Intelligent fire and wind prevention linkage method and system based on port quay crane meteorological perception

Abstract

The present application relates to the field of data processing technology, and discloses an intelligent fire and wind prevention linkage method and system based on meteorological perception of port quay cranes. The method includes: collecting equipment operation data through a multi-dimensional sensing unit, constructing a perception feature vector and calculating the working condition load index; according to the feature vector and the load index, the protection margin coefficient is calculated through a boundary mapping algorithm to generate an operation toughness value; based on the toughness value, a correlation analysis is performed to obtain the wind-fire coupling risk index and the disaster cascade impact; the prediction value is calculated according to the risk index and the impact, and the response matching degree is output; the strategy coefficient is adjusted according to the matching degree and fed back to the feature vector. The present application establishes a dynamic protection mechanism based on the actual bearing capacity of the equipment, so that it can maximize the operating time of the equipment while ensuring safety, while improving the system's ability to cope with complex disasters.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an intelligent fire and wind prevention linkage method and system based on port quay crane meteorological perception. Background Art

[0002] With the continuous improvement of port automation, intelligent quay cranes play an increasingly important role in container loading and unloading operations. Existing quay crane protection systems usually use independent wind protection systems and fire protection systems. The wind protection system mainly includes a wind speed monitoring device and a brake actuator, which triggers the brake protection when the wind speed exceeds the preset threshold; the fire protection system includes a temperature sensor and a fire fighting device, which is responsible for monitoring and handling fire hazards of the equipment. This discrete protection solution has accumulated rich practical experience in preventing a single type of disaster.

[0003] However, the existing protection schemes have obvious shortcomings: first, the wind protection system and the fire protection system are independent of each other, lacking an effective information sharing and collaborative decision-making mechanism, and are unable to cope with compound disaster risks such as equipment overheating caused by strong winds; second, the use of fixed protection thresholds for protection control fails to fully consider the actual bearing capacity of the equipment under different working conditions, and often results in excessive or insufficient protection; third, the control strategy lacks adaptive capabilities and is difficult to dynamically adjust according to the real-time status of the equipment, reducing the accuracy and effectiveness of the protection measures. Summary of the invention

[0004] The present application provides an intelligent fire and wind prevention linkage method and system based on port quay crane meteorological perception, which is used to break through the limitations of traditional fixed thresholds and establish a dynamic protection mechanism based on the actual bearing capacity of the equipment, so that it can maximize the operating time of the equipment while ensuring safety, while improving the system's ability to cope with complex disasters.

[0005] In the first aspect, the present application provides an intelligent fire and wind prevention linkage method based on port quay crane meteorological perception, and the intelligent fire and wind prevention linkage method based on port quay crane meteorological perception includes: collecting quay crane equipment operation data through a multidimensional sensing unit, combining equipment status records, constructing an equipment perception feature vector, and calculating the operating condition load index; according to the equipment perception feature vector and the operating condition load index, calculating the protection margin coefficient through a boundary mapping algorithm to generate an equipment operation resilience value; based on the equipment operation resilience value, performing correlation analysis on real-time monitoring data to form a wind-fire coupling risk index and a disaster cascade impact degree; according to the wind-fire coupling risk index and the disaster cascade impact degree, calculating the operation capacity prediction value, and outputting the control response matching degree; according to the control response matching degree, adjusting the protection strategy adaptation coefficient, and feeding back the execution result to the equipment perception feature vector.

[0006] In a second aspect, the present application provides an intelligent fire and wind prevention linkage system based on port quay crane meteorological perception, and the intelligent fire and wind prevention linkage system based on port quay crane meteorological perception includes: The acquisition module is used to collect the operation data of the quay crane equipment through the multi-dimensional sensing unit, build the equipment perception feature vector based on the equipment status record, and calculate the working condition load index; A calculation module, used to calculate the protection margin coefficient according to the device perception feature vector and the working condition load index through a boundary mapping algorithm to generate an equipment operation toughness value; A correlation module, used to perform correlation analysis on the real-time monitoring data based on the equipment operation resilience value to form a wind-fire coupling risk index and a disaster cascade impact degree; An output module, used to calculate the operation capacity prediction value and output the control response matching degree according to the wind-fire coupling risk index and the disaster cascade impact degree; The feedback module is used to adjust the protection strategy adaptation coefficient according to the control response matching degree, and feed back the execution result to the device perception feature vector.

[0007] The third aspect of the present invention provides a computer device, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the computer device executes the above-mentioned intelligent fire and wind prevention linkage method based on port quay crane meteorological perception.

[0008] A fourth aspect of the present invention provides a computer-readable storage medium, which stores instructions. When the computer-readable storage medium is run on a computer, the computer executes the above-mentioned intelligent fire and wind prevention linkage method based on port quay crane meteorological perception.

[0009] In the technical solution provided by the present application, equipment operation data is collected through a multi-dimensional sensing unit, and the equipment perception feature vector is constructed in combination with the equipment status record, thereby realizing comprehensive perception and accurate characterization of the operation status of the quay crane, and providing a reliable data basis for subsequent protection decisions. The protection margin coefficient is calculated through a boundary mapping algorithm and the equipment operation toughness value is generated, and a dynamic protection boundary based on the actual carrying capacity is established, overcoming the limitations of the traditional fixed threshold solution. Correlation analysis is performed on real-time monitoring data to form a wind-fire coupling risk index and a disaster cascade impact degree, realizing intelligent identification and quantitative assessment of compound disaster risks. The operation capacity prediction value is calculated based on the wind-fire coupling risk index and the disaster cascade impact degree, and the control response matching degree is output to ensure the pertinence and timeliness of the protection measures. By adjusting the protection strategy adaptation coefficient and feeding back the execution results to the equipment perception feature vector, a complete closed-loop control mechanism is constructed to ensure the continuous optimization and dynamic adjustment of the protection strategy. At the algorithm feature level, the solution innovatively applies the boundary mapping algorithm to the calculation of protection margin, and significantly improves the accuracy of protection decisions by establishing a dynamic mapping relationship between equipment carrying capacity and protection strategy; at the same time, the association analysis algorithm is used to achieve coupled assessment of wind and fire risks, enhancing the system's ability to cope with compound disasters; in addition, the introduction of an adaptive matching algorithm optimizes the control response, effectively improving the implementation effect of protective measures. Overall, the solution has achieved a shift from passive protection to active prevention through the organic combination of multiple innovative algorithms, greatly improving the safe operation level of port quay cranes. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0011] Figure 1 This is a schematic diagram of an embodiment of an intelligent fire and wind prevention linkage method based on port quay crane meteorological perception in an embodiment of the present application; Figure 2 This is a schematic diagram of an embodiment of an intelligent fire and wind prevention linkage system based on port quay crane meteorological perception in an embodiment of the present application; Figure 3 It is a schematic block diagram of the structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0012] The embodiment of the present application provides an intelligent fire and wind prevention linkage method and system based on port quay crane meteorological perception. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0013] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 In the embodiment of the present application, an embodiment of the intelligent fire and wind prevention linkage method based on port quay crane meteorological perception includes: Step S101: Collecting the operation data of the quay crane equipment through a multi-dimensional sensing unit, building the equipment perception feature vector in combination with the equipment status record, and calculating the working condition load index; Step S102: Calculate the protection margin coefficient based on the equipment perception feature vector and the working condition load index through the boundary mapping algorithm to generate the equipment operation toughness value; Step S103: Based on the equipment operation resilience value, correlation analysis is performed on the real-time monitoring data to form a wind-fire coupling risk index and a disaster cascade impact degree; Step S104: Calculate the predicted value of the operational capability according to the wind-fire coupling risk index and the disaster cascade impact, and output the control response matching degree; Step S105: adjust the protection strategy adaptation coefficient according to the control response matching degree, and feed back the execution result to the device perception feature vector.

[0014] It is understandable that the execution subject of the present application can be an intelligent fire and wind prevention linkage system based on port quay crane meteorological perception, or a terminal or a server, which is not limited here. The present application embodiment is described by taking the server as the execution subject as an example.

[0015] Specifically, the operation data of the quay crane equipment is collected through a multidimensional sensing unit, which includes a wind speed sensor, a brake status detector and a fire monitoring device. The wind speed data collected by the wind speed sensor ranges from 0.5 to 4.6 m / s and is divided into levels 1 to 3 according to the wind force level. The brake status detector collects the working status signals (clamping / releasing) of the trolley brake, the lifting brake and the trolley brake. The fire monitoring device collects the fire warning signals of the high-voltage room and the electrical room. The equipment status record includes the equipment number (such as ASC311-ASC332) and the operating status (automatic / intermediate / maintenance). When constructing the equipment perception feature vector, the wind speed data, the brake status and the fire monitoring signal are combined in time series to form a multidimensional vector containing wind speed characteristics, status characteristics and fire characteristics. The working condition load index is calculated by analyzing the corresponding relationship between wind speed and brake response. According to the equipment perception feature vector and the working condition load index, the boundary mapping algorithm establishes a multidimensional mapping space of risk factors, and each dimension represents a risk factor (wind speed, brake status, fire risk). In this space, by analyzing the safe operation boundary of the equipment, the protection margin coefficient is calculated, which reflects the safety redundancy of the equipment under the current working conditions. The equipment operation toughness value is obtained by normalizing the protection margin coefficient, which represents the ability of the equipment to resist risks.

[0016] After obtaining the equipment operation resilience value, the real-time collected monitoring data is analyzed for correlation, and the wind-fire coupling risk index is established by analyzing the equipment status sequence (such as the situation where the ASC324 trolley brake is abnormal but the fire monitoring is normal). This index reflects the combined impact of wind speed and fire risk. At the same time, based on the analysis of risk transmission rules, the disaster cascade impact degree is formed to characterize the chain effect of multiple disasters.

[0017] According to the wind-fire coupling risk index and the disaster cascade impact, the wind and fire protection characteristic components are separated from the wind-fire coupling risk index through risk linkage decoupling to construct the operation risk characteristic chain. Combined with the disaster cascade impact, the disaster evolution flow chart is developed according to the brake response sequence to generate the safety characterization parameters of the operation area, and then the operation capacity prediction value is calculated. The prediction value is decomposed by three-dimensional vectors to extract the braking association characteristics, operation status characteristics and control response characteristics to form a multi-dimensional control coordination sequence, and the control response matching degree is output. According to the control response matching degree, the signal is split by the control response parser to obtain the braking control characteristic chain and the fire protection characteristic chain respectively. These two characteristic chains are mapped to the equipment operation space through the control effectiveness evaluator to form a protection control mapping matrix. The key control nodes in the matrix are extracted to construct the wind-fire linkage response spectrum to obtain the strategy adjustment sequence. The sequence is decomposed in time series through state interval division to obtain the risk protection segment and the fire protection segment, and the basic working condition signal and the disturbance working condition signal separated by the working condition feature extractor are combined to form the working condition characteristic spectrum. Through protection timing mapping and cross-validation, the device control response chain is generated, and after evaluation by the strategy coordination analyzer, the protection execution sequence is formed, and the protection strategy adaptation coefficient is reconstructed. The execution result is fed back to the device perception feature vector according to the feature mapping relationship to complete the linkage control cycle.

[0018] For example, when the wind speed of a certain port gantry crane ASC321 reached 4.6m / s (level 3 wind), the lifting brake status became abnormal. Through the analysis of the equipment perception feature vector, it was found that the equipment operating load index was low, and the protection margin coefficient calculated by boundary mapping indicated that the safety redundancy was insufficient. The correlation analysis showed that the wind-fire coupling risk index increased, and the disaster cascade impact indicated that there was a risk of equipment loss of control. The operation capacity prediction value based on this calculation triggered the control response and generated a stricter protection strategy adaptation coefficient. The system adjusted the control strategy of the lifting brake in time and successfully prevented the occurrence of equipment loss of control accidents.

[0019] In the embodiment of the present application, the equipment operation data is collected by a multi-dimensional sensing unit, and the equipment perception feature vector is constructed in combination with the equipment status record, so as to realize the comprehensive perception and accurate characterization of the operation status of the quay crane, and provide a reliable data basis for subsequent protection decisions. The protection margin coefficient is calculated by the boundary mapping algorithm and the equipment operation toughness value is generated, and a dynamic protection boundary based on the actual carrying capacity is established, which overcomes the limitations of the traditional fixed threshold scheme. The real-time monitoring data is correlated and analyzed to form the wind-fire coupling risk index and the disaster cascade impact degree, so as to realize the intelligent identification and quantitative evaluation of the compound disaster risk. The operation capacity prediction value is calculated according to the wind-fire coupling risk index and the disaster cascade impact degree, and the control response matching degree is output to ensure the pertinence and timeliness of the protection measures. By adjusting the protection strategy adaptation coefficient and feeding back the execution result to the equipment perception feature vector, a complete closed-loop control mechanism is constructed to ensure the continuous optimization and dynamic adjustment of the protection strategy. At the algorithm feature level, the solution innovatively applies the boundary mapping algorithm to the protection margin calculation, and significantly improves the accuracy of protection decisions by establishing a dynamic mapping relationship between equipment carrying capacity and protection strategy. At the same time, the correlation analysis algorithm is used to realize the coupled assessment of wind and fire risks, enhancing the system's ability to cope with complex disasters. In addition, the introduction of an adaptive matching algorithm optimizes the control response, effectively improving the implementation effect of protection measures.

[0020] In a specific embodiment, the process of executing step S101 may specifically include the following steps: (1) The wind speed value, brake status signal and fire monitoring signal of the quay crane equipment are collected through the wind speed sensor, brake status detector and fire monitoring device to obtain the original monitoring data; (2) The original monitoring data is classified and sorted according to the equipment number and operating status to obtain the basic data group; (3) Based on the basic data set, the feature extraction module is used to analyze the relationship between wind speed and brake response, the corresponding relationship between equipment status and fire monitoring signals, and the synergistic relationship between brakes to generate a feature marker sequence; (4) Match and analyze the feature marker sequence with wind speed data, brake status data, and fire monitoring data to form a device perception feature vector; (5) Based on the equipment perception feature vector, combined with the wind force level parameters and brake state parameters, the working condition bearing capacity is calculated to obtain the working condition bearing index.

[0021] Specifically, the wind speed of the quay crane equipment is monitored in real time through the wind speed sensor, and the effective collection range of the wind speed value is 0.5-4.6m / s. The brake status detector collects the status signals of the trolley brake, hoisting brake and trolley brake, including the clamping state and the release state. The fire monitoring device is responsible for collecting the fire warning signals of the high-voltage room and the electrical room. The original monitoring data collected by these three types of sensors are recorded at a fixed sampling frequency, and each data contains timestamp information. When classifying and arranging the collected original monitoring data, an independent data group is established according to the equipment number (such as ASC311-ASC332), and each data group is further classified into two levels according to the equipment operation status (automatic, intermediate, maintenance). Abnormal values ​​are eliminated during the data sorting process, such as wind speed values ​​that exceed the range or signal interruption status records. Each basic data group contains a complete monitoring record of the equipment under various operating conditions.

[0022] Based on the sorted basic data set, the relationship between wind speed and brake response is analyzed. The time series of the brake switching from the release state to the clamping state when the wind speed increases reflects the response characteristics of the brake to wind speed changes. The corresponding relationship between the equipment state and the fire monitoring signal is reflected in the distribution law of the fire warning signal under different operating conditions. The synergistic relationship between the brakes is obtained by analyzing the sequence and time interval of the three brake states of the trolley, hoist and trolley. The results of the above three types of relationship analysis form a feature mark sequence, which records the response mode of the equipment to changes in the external environment. The feature mark sequence is matched and analyzed with the real-time wind speed data, brake state data and fire monitoring data. The sliding time window method is used to extract the wind speed peak value, the number of brake state conversions, the fire warning signal intensity and other feature quantities in each time window. After standardization, the feature quantities form the equipment perception feature vector, which fully reflects the operating status of the equipment at the current moment.

[0023] According to the characteristic quantity in the device perception characteristic vector, combined with the wind force level classification standard (level 1: 0.5-1.4m / s, level 2: 1.9-2.9m / s, level 3: 3.5-4.6m / s) and brake state parameters (clamping time, release time, response delay), the working condition bearing capacity is calculated. The benchmark bearing capacity corresponding to the current wind force level is determined, and then it is corrected according to the stability of the brake state to obtain the working condition bearing index. This index reflects the comprehensive ability of the equipment to withstand wind loads and respond to fire risks under the current working conditions.

[0024] Taking a quay crane at the port as an example, when the wind speed sensor collected data on the wind speed gradually increasing from 1.4m / s to 2.9m / s, the brake state detector recorded the complete state sequence in which the trolley brake entered the clamping state, and then the lifting brake and the trolley brake responded in sequence. The fire monitoring device maintained normal signal output during this period. The original monitoring data was classified according to the equipment number ASC315 and marked as being in automatic operation. Data analysis shows that the brake response of the equipment has obvious synergy, and the state change of the trolley brake is 0.5 seconds ahead of other brakes, which constitutes the key feature of the feature marker sequence. The equipment perception feature vector after matching analysis reflects the sensitive response of the equipment to wind speed changes. Combined with the level 2 wind force level standard and the stable clamping state of the brake, the calculated working condition load index shows that the equipment has sufficient load-bearing capacity and can continue to operate safely.

[0025] In a specific embodiment, the process of executing step S102 may specifically include the following steps: (1) Extract stable operation parameters, dynamic response parameters, and safety threshold parameters from the device perception feature vector through the device load matrix extractor to generate a device capability attribute set; (2) Use the wind speed response correlator to segment and pair the load index according to different wind force levels to form a wind speed load correspondence table; (3) Based on the equipment capability attribute set, a three-dimensional safety envelope surface is constructed, and the wind speed load correspondence table is mapped to the envelope surface to obtain the equipment safe operation domain; (4) Calculate the boundary gradient of the equipment's safe operating domain, and generate the protection margin coefficient based on the equipment's operating status and braking response time; (5) Adaptively match the protection margin coefficient with the real-time monitoring data, calculate the equipment's stable operating parameters and emergency response parameters, and obtain the equipment's operating resilience value.

[0026] Specifically, the equipment load matrix extractor extracts stable operation parameters from the equipment perception feature vector, including the stable clamping time of the brake at different wind speeds, the wind load bearing capacity of the equipment during operation, the fire alarm threshold, etc. The dynamic response parameters include the response delay of each brake, the state switching rate, and the fire signal change rate. The safety threshold parameters include the upper wind speed limit, the brake state switching critical point, and the fire warning trigger value. These parameters are organized into a set of equipment capability attributes according to the following formula: in, is a set of device capability attributes, To stabilize the operating parameters, is the dynamic response parameter, is the safety threshold parameter, , , is the weight coefficient of each parameter, and n is the parameter dimension.

[0027] The wind speed response associator pairs the load index in sections according to the wind force level (level 1: 0.5-1.4m / s, level 2: 1.9-2.9m / s, level 3: 3.5-4.6m / s), and generates a wind speed load correspondence table using the following formula: in, is the wind speed load correspondence table, is the characteristic value of wind speed under different wind force levels, is the corresponding working condition load index, and m is the wind force level.

[0028] When constructing a three-dimensional security envelope based on the device capability attribute set, the following formula is used: in, For the device safe operation domain, and They are respectively the mapping functions of the equipment capability attribute set and the wind speed load correspondence table.

[0029] The boundary gradient of the equipment's safe operation domain is calculated, and the protection margin coefficient is generated by the following formula in combination with the equipment's operating status and braking response time: in, is the protection margin factor, is the boundary gradient of the safe operation domain, is the equipment operation status parameter, is the braking response time, and is the adjustment factor.

[0030] Generate device operation toughness value through adaptive matching: in, The toughness value for the device operation. To monitor data in real time, is the adaptive matching function.

[0031] Taking a quay crane at a port as an example, when the wind speed transitions from level 2 to level 3, the equipment load matrix extractor extracts parameters such as the stable clamping time and wind load bearing capacity of the trolley brake from the equipment perception feature vector to generate a set of equipment capacity attributes. The wind speed response associator pairs the working load index with level 3 wind force (3.5-4.6m / s) to form a wind speed load correspondence table. The three-dimensional safety envelope constructed based on these two sets of data shows that the equipment is in a critical operating state. The boundary gradient calculation results are combined with the current automatic operating state of the equipment and the 0.5-second response time of the brake to generate a lower protection margin coefficient. After the coefficient is adaptively matched with the real-time monitored level 3 wind speed data, the calculated equipment operation toughness value indicates that the protection strategy needs to be adjusted in time.

[0032] In a specific embodiment, the process of executing step S103 may specifically include the following steps: (1) The risk identification unit extracts wind speed monitoring signals, brake status signals, and fire warning signals from real-time monitoring data to generate a wind and fire monitoring feature group; (2) Use the protection level evaluator to map the equipment operation toughness value to form an equipment protection level sequence; (3) Cross-match the wind and fire monitoring feature group and the equipment protection level sequence according to the wind and fire coupling rules to obtain the risk-related feature chain; (4) Analyze the transfer relationship of the risk-related feature chain through the risk transfer evaluator to generate a wind-fire coupling risk index; (5) Based on the temporal variation trend of the wind-fire coupling risk index, a disaster spread situation map is constructed to form the disaster cascade impact degree.

[0033] Specifically, the risk identification unit first extracts the wind speed monitoring signal, brake status signal and fire warning signal from the real-time monitoring data to generate a wind and fire monitoring feature group. In specific implementation, the wind speed monitoring signal is collected by the wind speed sensor installed on the port quay crane, and the data includes wind speed value, wind direction angle and wind duration; the brake status signal is collected by the brake status detector, which records the working status, response time and braking force of the brake; the fire warning signal is collected by the fire monitoring device, which includes temperature value, smoke concentration and fire source location information. These original signals are formed into a wind and fire monitoring feature group after signal preprocessing, feature extraction and feature fusion, which is expressed in the form of a multidimensional vector and includes wind speed features, brake features and fire features. The protection level evaluator performs state mapping for the equipment operation toughness value to form an equipment protection level sequence. The equipment operation toughness value is a quantitative indicator reflecting the ability of the quay crane to continue to operate safely under different harsh conditions. It is calculated by adaptive matching of the protection margin coefficient with the equipment stable operation parameters and emergency response parameters. The protection level evaluator uses a hierarchical division algorithm to map the toughness value to a preset protection level interval and generate a device protection level sequence. Each element corresponds to the protection level at a specific point in time, and the value range is from Level I (highest protection) to Level V (lowest protection).

[0034] The wind and fire monitoring feature group and the equipment protection level sequence are cross-matched according to the wind and fire coupling rules to obtain the risk-related feature chain. The wind and fire coupling rules define the mutual influence relationship between wind speed signals, brake status and fire signals, including the acceleration effect of wind speed on fire spread, the thermal damage effect of fire on brake performance, and the influence of brake status on risk tolerance. The cross-matching process uses the time series correlation analysis method to identify the correspondence between each feature in the wind and fire monitoring feature group and the protection level, and construct a feature association network to finally form a risk-related feature chain.

[0035] The risk transfer evaluator analyzes the transfer relationship of the risk-related feature chain and generates a wind-fire coupling risk index. The risk transfer evaluator analyzes the transfer path and impact intensity between wind speed changes, fire development and brake performance degradation through a disaster chain reaction model. The transfer relationship analysis uses the path analysis method in graph theory to calculate the transfer coefficient and cumulative effect between each node in the risk-related feature chain, identify the key risk transfer path and risk amplification point, and finally quantify the wind-fire coupling risk index, which comprehensively reflects the comprehensive risk status of fire risk and brake performance under the current wind speed conditions. Based on the temporal change trend of the wind-fire coupling risk index, a disaster spread situation map is constructed to form a disaster cascade impact degree. The temporal change trend is obtained by extracting the change rate and directional characteristics of the wind-fire coupling risk index in a continuous time window, and a trend prediction algorithm is used to estimate the future risk evolution. The disaster spread situation map shows the risk propagation path and impact range between the various components of the quay crane equipment in the form of spatial distribution, and intuitively displays the high-risk area through a heat map. The disaster cascade impact quantifies the severity and scope of the chain reaction of disaster events, taking into account the possibility and depth of impact of the initial disaster triggering secondary disasters.

[0036] For example, in a port quay crane under strong wind weather conditions, wind speed monitoring data showed that the current wind speed reached 15 m / s, the wind direction was perpendicular to the quay crane main beam, and the duration had exceeded 30 minutes; brake status monitoring data showed that the response time of some brakes was extended to 1.2 times the normal value, and the braking force decreased by 10%; the fire monitoring device detected that the temperature of the substation room abnormally increased to 65°C, and the smoke concentration increased slightly. The risk identification unit combined these data to generate a wind and fire monitoring feature group, recording three key features: continuous excessive wind speed, reduced braking performance, and abnormal temperature. At the same time, based on the previously calculated equipment operation resilience value of 0.82, the protection level assessor mapped it to a level II protection state, indicating that the equipment has a certain ability to resist wind and fire but is close to the warning line. The wind and fire coupling rule determines that the current wind speed conditions will increase the spread speed of potential fire sources, and the reduced brake performance has a significant impact on wind resistance. After cross-matching, a risk-related feature chain is formed, and the association path of wind speed-fire-braking performance is confirmed. The risk transfer evaluator calculated that the wind-fire coupling risk index was 0.76, which was at a medium-high risk level, and predicted that if the wind speed continued to increase, the risk index would exceed the 0.85 warning value within 30 minutes. Based on this trend, the system constructed a disaster spread situation map, showing that the fire risk in the substation room may spread to the main control cabinet, and finally formed a disaster cascade impact assessment result, guiding the system to adjust the protection strategy, start the enhanced brake pre-tightening measures in advance and activate the automatic fire extinguishing device in the substation room, effectively preventing the occurrence of potential wind-fire compound disasters.

[0037] In a specific embodiment, the process of executing step S104 may specifically include the following steps: (1) Separate the wind and fire protection characteristic components from the wind-fire coupling risk index through the risk linkage decoupling unit to generate an operational risk characteristic chain; (2) Using the disaster situation analyzer, the disaster cascade impact is expanded according to the brake response sequence to form a disaster evolution flow diagram; (3) Based on the operation risk characteristic chain and disaster evolution flow diagram, an automatic operation tolerance judgment matrix is ​​constructed to obtain the safety characterization parameters of the operation area; (4) Mapping the safety characterization parameters of the operating area to the real-time equipment state space to generate the predicted value of the operating capability; (5) Perform three-dimensional vector decomposition on the predicted value of the operating capability, extract the braking association characteristics, operating status characteristics, and control response characteristics, and form a multi-dimensional control coordination sequence; (6) The control signal is fitted and reconstructed according to the multi-dimensional control coordination sequence, and the control response matching degree is output.

[0038] Specifically, the risk linkage decoupling unit separates the wind and fire prevention characteristic components from the wind-fire coupling risk index to generate an operation risk characteristic chain. In specific implementation, the wind-fire coupling risk index contains multi-dimensional information such as the impact of wind speed on equipment, the risk of fire spread, and the interaction between the two. The decoupling unit splits the coupling risk index into independent wind prevention characteristic components and fire prevention characteristic components through the feature decomposition technology. The separation process uses a signal decomposition algorithm to identify the independent characteristics of each characteristic component in the time domain and frequency domain, and extract the direct characteristics of the impact of wind speed on the brake, the independent characteristics of fire risk, and the coupling characteristics of the interaction between the two. These separated features are reorganized according to the time series correlation and impact degree to form an operation risk characteristic chain, which shows the direct impact path of wind speed changes and fire risks on the safety of quay crane operations. The disaster situation analyzer expands the disaster cascade impact degree according to the brake response sequence to form a disaster evolution flow chart. The disaster cascade impact degree characterizes the propagation characteristics and impact range of secondary disasters caused by the initial disaster event, and the brake response sequence reflects the dynamic response process of the quay crane braking system when facing risks. The disaster situation analyzer matches the disaster cascade impact with the brake response sequence in time series, and analyzes the corresponding relationship between each stage of disaster development and the change of brake state. Through the event tree analysis method, the evolution path and results of disaster events under different braking response conditions are predicted, multiple possible disaster development paths are constructed, and the probability of occurrence and impact of each path are evaluated. The disaster evolution flow diagram shows the complete evolution process of the disaster from the initial state to various possible results in the form of a directed graph. The nodes represent the disaster state and the edges represent the state transition conditions.

[0039] According to the operation risk characteristic chain and the disaster evolution flow chart, the automatic operation tolerance judgment matrix is ​​constructed to obtain the safety characterization parameters of the operation area. The automatic operation tolerance judgment matrix is ​​a decision-making tool for evaluating the safe operation capability of the quay crane equipment under the current wind and fire risk conditions. During the construction process, the risk components of the operation risk characteristic chain are mapped to the key nodes of the disaster evolution flow chart to analyze the possibility of disaster development corresponding to each risk factor. By setting the risk tolerance threshold and safety margin parameters, the risk space is divided into safe operation area, restricted operation area and prohibited operation area. The judgment matrix calculation takes into account multiple factors such as wind speed level, fire risk level, brake response capability, etc., and comprehensively evaluates to form the safety characterization parameters of the operation area. The parameters are expressed in the form of multidimensional vectors, which quantitatively describe the safe operation capability of each functional area of ​​the quay crane under the current wind and fire conditions. The safety characterization parameters of the operation area are mapped to the real-time equipment state space to generate the operation capability prediction value. The real-time equipment state space is a multidimensional space model that describes the current operating state of the quay crane, which contains key state variables such as position, speed, acceleration, and load. The mapping process uses a state space conversion algorithm to establish a corresponding relationship between the safety characterization parameters and the equipment state variables, and analyze the restrictions of the safety constraints on the equipment operation status. By calculating the distance between the safety boundary and the current state, the maximum operating capacity that the equipment can perform while ensuring safety is evaluated. The operating capacity prediction value comprehensively represents the safe operating range and efficiency level of the quay crane under the current wind and fire risk conditions, and quantifies the maximum safe operating capacity of the equipment in percentage form.

[0040] The three-dimensional vector decomposition of the operation capability prediction value is performed to extract the braking association characteristics, operation status characteristics and control response characteristics to form a multi-dimensional control coordination sequence. Three-dimensional vector decomposition is a technical means to deconstruct the operation capability prediction value into a more operational control feature set. The braking association characteristics describe the correlation between the braking system parameters and safe operation, including braking force requirements, response time requirements and braking coordination; the operation status characteristics reflect the safety constraints of the quay crane motion parameters, including speed limits, acceleration limits and position limits; the control response characteristics characterize the control system's response requirements to wind and fire risks, including response sensitivity, control accuracy and stability requirements. These three groups of characteristics form a multi-dimensional control coordination sequence through feature association analysis. The sequence describes the synergistic relationship between the braking system, the operation system and the control system to ensure the consistent response of the three systems under wind and fire risk conditions. The control signal fitting reconstruction is performed according to the multi-dimensional control coordination sequence, and the control response matching degree is output. The control signal fitting reconstruction is a technical process of converting the control coordination sequence into a specific control signal. The fitting reconstruction adopts the model predictive control algorithm, constructs the control objective function based on the multi-dimensional control coordination sequence, and optimizes the generation of a control signal sequence that meets the safety constraints. The control signals include brake control signals, speed control signals and position control signals, which act on different actuators of the quay crane respectively. The control response matching degree evaluates the matching degree between the generated control signals and the wind and fire risk protection requirements. A high matching degree indicates that the control strategy can effectively respond to the current wind and fire risk situation.

[0041] For example, a port gantry crane faces a compound risk situation with a wind speed of 18 m / s and abnormal temperature in the substation, and the wind-fire coupling risk index is 0.82. The risk linkage decoupling unit analysis found that the wind protection characteristic component is 0.65, the fire protection characteristic component is 0.45, and the interactive impact component is 0.25. It also generates an operation risk characteristic chain, clarifies the direct impact path of wind speed on the braking system and the impact path of fire risk on the electrical system. At the same time, the disaster situation analyzer expands the disaster cascade impact degree according to the brake response sequence to form a disaster evolution flow chart, predicting that under the current state, if the abnormal temperature in the substation is not handled, it may spread to the control cabinet area within 15 minutes, and strong wind conditions will accelerate the spread of the fire and affect the performance of the brake. Based on the operation risk characteristic chain and the disaster evolution flow chart, an automatic operation tolerance judgment matrix was constructed, and the safety characterization parameters of the main hoist area, the trolley operation area, and the trolley operation area were calculated to be 0.72, 0.65, and 0.78. These parameters are mapped to the real-time equipment state space to generate an operating capacity prediction value of 75%, indicating that under the current wind and fire conditions, the quay crane can only operate safely at 75% of its normal operating capacity. Through three-dimensional vector decomposition, the system extracts braking association characteristics (braking force needs to be increased by 30%, response time needs to be shortened by 15%), operating status characteristics (speed limit is 60% of normal value, acceleration limit is 50% of normal value) and control response characteristics (response sensitivity increased by 25%, control accuracy improved by 20%), forming a multi-dimensional control coordination sequence. Based on this sequence, the system performs control signal fitting and reconstruction, and outputs a control response matching degree of 0.85. Based on this, the system automatically adjusts the braking force, limits the operating speed, and enhances the control response sensitivity, effectively ensuring the safe operation of the quay crane in a complex risk environment.

[0042] In a specific embodiment, the process of executing step S105 may specifically include the following steps: (1) The control response parser is used to split the control response matching signal and generate the brake control feature chain and the fire protection feature chain; (2) Use the control effectiveness evaluator to map the brake control feature chain and the fire protection feature chain to the equipment operation space to form a protection control mapping matrix; (3) Extract key control nodes according to the protection control mapping matrix, construct the wind-fire linkage response map, and obtain the strategy adjustment sequence; (4) Match the strategy adjustment sequence in sections according to the equipment operation status to generate the protection strategy adaptation coefficient; (5) extracting the state feedback component from the protection strategy adaptation coefficient through the response feature analyzer to form a state update feature group; (6) Reconstruct the state update feature group according to the feature mapping relationship and feed it back to the device perception feature vector.

[0043] Specifically, the control response parser performs signal splitting on the control response matching degree to generate a braking control feature chain and a fire protection feature chain. In specific implementation, the control response matching degree is a comprehensive indicator to measure the degree of matching between the control strategy and the wind and fire risk protection requirements, and contains information on different protection strategies for risks and fires. The control response parser uses signal decomposition technology to separate the matching degree indicator into independent braking control components and fire protection components. The signal splitting process uses a feature extraction algorithm to identify the features related to the braking system and the features related to fire protection in the control response, and constructs a braking control feature chain and a fire protection feature chain respectively. The braking control feature chain includes braking force adjustment parameters, response time optimization parameters, and position restriction parameters; the fire protection feature chain includes temperature monitoring thresholds, fire source isolation strategies, and fire extinguishing system activation conditions. The control effectiveness evaluator maps the braking control feature chain and the fire protection feature chain to the equipment operation space to form a protection control mapping matrix. The equipment operation space is a mathematical model that describes the operating status of each component of the quay crane, including key operating parameters such as position, speed, and load. The mapping process uses the state space transformation method to establish a corresponding relationship between the control characteristics and the equipment operating parameters, and analyze the impact of different control strategies on the equipment operating status. The protection control mapping matrix is ​​represented in the form of a two-dimensional matrix, with rows representing different control characteristics, columns representing equipment operating parameters, and matrix element values ​​reflecting the degree of influence of control characteristics on operating parameters. The matrix clearly shows the quantitative relationship between each protection control strategy and the equipment operating capacity, providing a basis for subsequent strategy optimization.

[0044] According to the protection control mapping matrix, the key control nodes are extracted, the wind-fire linkage response map is constructed, and the strategy adjustment sequence is obtained. The key control nodes are the control points that have the most significant impact on the safe operation of the equipment. They are identified from the protection control mapping matrix through the matrix sensitivity analysis method. The identification process calculates the influence weight of each element in the matrix, and selects the nodes whose influence exceeds the threshold as key control nodes. The wind-fire linkage response map shows the linkage relationship between the key control nodes in the form of a network diagram. The nodes represent the control points, the edges represent the influence relationship between the control points, and the weights represent the influence intensity. Through the map analysis, the system identifies the optimal control path and forms a strategy adjustment sequence. The sequence is represented in the form of a set of control instructions arranged in time order, including the adjustment timing, adjustment amplitude and duration of each control point. The strategy adjustment sequence is segmented and matched according to the equipment operation status to generate the protection strategy adaptation coefficient. The equipment operation status can be divided into multiple operating conditions according to the operating load, speed range and environmental conditions, such as light load condition, heavy load condition, acceleration condition and deceleration condition. The segmented matching process determines the current operating condition of the equipment through the state recognition algorithm, and then selects the control strategy subset suitable for the condition from the strategy adjustment sequence. For different working conditions, the system adjusts the amplitude and response speed of the control parameters to form a working condition adaptive control strategy. The protection strategy adaptability coefficient quantifies the adaptability of the control strategy to different working conditions. A high adaptability coefficient indicates that the control strategy can fully consider the working condition characteristics of the equipment and maximize the equipment's operating capacity while ensuring safety.

[0045] The response feature analyzer extracts the state feedback component from the protection strategy adaptation coefficient to form a state update feature group. The state feedback component reflects the change of the equipment state after the control strategy is executed, and is an important basis for evaluating the control effect. The extraction process uses the feedback signal analysis method to compare the changes in the equipment state parameters before and after the control, and identify the state change characteristics caused by the control strategy. The state update feature group includes equipment position change characteristics, speed change characteristics, brake state change characteristics and system response characteristics, etc. These characteristics reflect the actual execution effect of the control strategy and provide data support for subsequent control optimization. The state update feature group is reconstructed according to the feature mapping relationship and fed back to the equipment perception feature vector. The feature mapping relationship defines the correspondence rules between the state update feature and the equipment perception feature, and the mutual conversion of the two feature spaces is realized through the feature conversion algorithm. The reconstruction process converts the state update feature into a format compatible with the equipment perception feature vector, merges it with the original feature vector, and updates the relevant parameters in the equipment perception feature vector. This feedback mechanism forms a complete closed-loop control, enabling the system to continuously optimize the protection strategy according to the control execution effect and improve the system's adaptability to wind and fire risks.

[0046] For example, when a certain port quay crane is in strong wind conditions and abnormal temperature occurs in the electrical area, the control response analyzer splits the control response matching degree and separates the braking control requirements and fire protection requirements. The control effectiveness evaluator maps these requirements to the equipment operation space, generates a protection control mapping matrix, and clearly displays the impact range of each control strategy. The system extracts key nodes such as the main brake control point, auxiliary brake control point, and electrical cabinet cooling control point, constructs a linkage response map, and forms the optimal control path and strategy sequence. According to the heavy-load operating conditions currently performed by the quay crane, the system matches and adjusts the strategy to generate a protection strategy adaptation coefficient suitable for heavy-load conditions. After executing the control, the response feature analyzer extracts feedback information, generates a state update feature group, and feeds it back to the equipment perception feature vector to complete the control closed loop and ensure the safe operation of the quay crane in a complex risk environment.

[0047] In a specific embodiment, the process of performing segmented matching of the policy adjustment sequence according to the device operation status may specifically include the following steps: (1) The strategy adjustment sequence is decomposed in time series through the state interval divider to obtain the risk protection segment and the fire protection segment; (2) Using the operating condition feature extractor to separate the basic operating condition signal and the disturbance operating condition signal from the equipment operation status to form an operating condition feature spectrum; (3) Based on the timestamp information of the risk protection segment and the fire protection segment, a protection timing mapping table is constructed to obtain the protection priority sequence; (4) Cross-validate the protection priority sequence with the operating condition characteristic spectrum to generate the equipment control response chain; (5) Use the strategy coordination analyzer to evaluate the reliability of the device control response chain and form a protection execution sequence; (6) Reconstruct the strength value of the protection execution sequence and generate the protection strategy adaptation coefficient.

[0048] Specifically, the state interval divider needs to clearly divide the time window in the process of time series decomposition of the strategy adjustment sequence. For wind speed data, it is segmented according to wind force level (level 1: 0.5-1.4m / s, level 2: 1.9-2.9m / s, level 3: 3.5-4.6m / s); for fire monitoring data, it is segmented according to temperature change rate and fire warning threshold. Through this segmentation method, two independent time series data groups, risk protection segment and fire protection segment, are obtained. When the working condition feature extractor separates data from the equipment operation status, it identifies the basic working condition signals, including the wind speed range, brake response time, equipment vibration characteristics and other standard operating parameters of the quay crane during normal operation. At the same time, the disturbance working condition signals are extracted, including non-standard operating parameters such as equipment shaking caused by sudden strong winds, abnormal brake response, and fire warning triggering. After these signals are standardized, they form working condition characteristic spectra, which fully record the operating characteristics of the equipment under different working conditions.

[0049] During the construction of the protection timing mapping table, the timestamp information of the risk protection segment and the fire protection segment is read to record the triggering time and duration of each protection action. Then the protection priority is determined according to the risk level and the fire spread trend. For example, when a brake abnormality is detected and accompanied by a temperature increase, the relevant protection action will be given a higher priority. The generated protection priority sequence contains a complete timing arrangement of protection actions. When cross-validating the protection priority sequence with the operating condition characteristic spectrum, it is necessary to ensure that each protection action matches the current operating condition. The specific approach is to compare the execution conditions of the protection action with the operating condition characteristics to verify whether the protection action meets the current operating condition requirements. This process outputs the device control response chain and records the complete control action sequence.

[0050] When the strategy coordination analyzer conducts reliability assessment on the device control response chain, it focuses on three aspects: the timing rationality of the control action, the appropriateness of the action amplitude, and the coordination between actions. By analyzing the correlation between adjacent control actions, it is determined whether there is a conflict or repetition, and an optimized protection execution sequence is formed. The strength value of the protection execution sequence is reconstructed to obtain the protection strategy adaptation coefficient. During the reconstruction process, the execution intensity of each control action is adjusted so that it can meet the protection requirements without causing excessive interference to the operation of the equipment. The adjustment parameters include braking torque, response delay, execution time, etc.

[0051] Taking a port quay crane as an example, when the wind speed rises from level 1 to level 3, the state interval divider decomposes the strategy adjustment sequence into risk protection segments and fire protection segments. The operating condition feature extractor identifies abnormal features such as sudden changes in wind speed and brake response delays from the equipment operation status. The protection timing mapping table constructed based on these timing features shows that the protection action of the trolley brake has the highest priority. After cross-validation, the equipment control response chain contains a complete action sequence from brake pre-tightening to full braking. The strategy coordination analyzer evaluated and found that the control actions of the sequence were coherent and conflict-free, and the reconstructed protection strategy adaptation coefficient not only ensured the braking effect, but also avoided severe shaking of the equipment.

[0052] The above describes the intelligent fire and wind prevention linkage method based on port quay crane meteorological perception in the embodiment of the present application. The following describes the intelligent fire and wind prevention linkage system based on port quay crane meteorological perception in the embodiment of the present application. Please refer to Figure 2 In the embodiment of the present application, an embodiment of the intelligent fire and wind prevention linkage system based on port quay crane meteorological perception includes: The acquisition module is used to collect the operation data of the quay crane equipment through the multi-dimensional sensing unit, build the equipment perception feature vector based on the equipment status record, and calculate the working condition load index; A calculation module, used to calculate the protection margin coefficient according to the device perception feature vector and the working condition load index through a boundary mapping algorithm to generate an equipment operation toughness value; A correlation module, used to perform correlation analysis on the real-time monitoring data based on the equipment operation resilience value to form a wind-fire coupling risk index and a disaster cascade impact degree; An output module, used to calculate the operation capacity prediction value and output the control response matching degree according to the wind-fire coupling risk index and the disaster cascade impact degree; The feedback module is used to adjust the protection strategy adaptation coefficient according to the control response matching degree, and feed back the execution result to the device perception feature vector.

[0053] Through the collaboration of the above components, the equipment operation data is collected through multi-dimensional sensing units, and the equipment perception feature vector is constructed in combination with the equipment status record, which realizes the comprehensive perception and accurate characterization of the operation status of the quay crane, providing a reliable data basis for subsequent protection decisions. The protection margin coefficient is calculated through the boundary mapping algorithm and the equipment operation toughness value is generated. A dynamic protection boundary based on the actual carrying capacity is established, overcoming the limitations of the traditional fixed threshold scheme. The real-time monitoring data is correlated and analyzed to form the wind-fire coupling risk index and the disaster cascade impact degree, realizing the intelligent identification and quantitative evaluation of compound disaster risks. The operation capacity prediction value is calculated according to the wind-fire coupling risk index and the disaster cascade impact degree, and the control response matching degree is output to ensure the pertinence and timeliness of the protection measures. By adjusting the protection strategy adaptation coefficient and feeding back the execution results to the equipment perception feature vector, a complete closed-loop control mechanism is constructed to ensure the continuous optimization and dynamic adjustment of the protection strategy. At the algorithm feature level, the solution innovatively applies the boundary mapping algorithm to the calculation of protection margin, and significantly improves the accuracy of protection decisions by establishing a dynamic mapping relationship between equipment carrying capacity and protection strategy; at the same time, the association analysis algorithm is used to achieve coupled assessment of wind and fire risks, enhancing the system's ability to cope with compound disasters; in addition, the introduction of an adaptive matching algorithm optimizes the control response, effectively improving the implementation effect of protective measures. Overall, the solution has achieved a shift from passive protection to active prevention through the organic combination of multiple innovative algorithms, greatly improving the safe operation level of port quay cranes.

[0054] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0055] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0056] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0057] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0058] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0059] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0060] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent fire and wind prevention linkage method based on port quay crane meteorological perception, characterized in that: The intelligent fire and wind prevention linkage method based on port quay crane meteorological perception includes: The multi-dimensional sensing unit collects the operation data of the quay crane equipment, combines it with the equipment status record, constructs the equipment perception feature vector, and calculates the working condition load index; According to the equipment perception feature vector and the working condition load index, the protection margin coefficient is calculated through the boundary mapping algorithm to generate the equipment operation toughness value; Based on the equipment operation resilience value, correlation analysis is performed on the real-time monitoring data to form a wind-fire coupling risk index and a disaster cascade impact degree; According to the wind-fire coupling risk index and the disaster cascade impact, the operation capacity prediction value is calculated and the control response matching degree is output; According to the control response matching degree, the protection strategy adaptation coefficient is adjusted, and the execution result is fed back to the device perception feature vector.

2. The intelligent fire and wind prevention linkage method based on port quay crane meteorological perception according to claim 1 is characterized in that: The multi-dimensional sensing unit is used to collect the operation data of the quay crane equipment, and the equipment state record is combined to construct the equipment perception feature vector, and the working condition load index is calculated, including: The wind speed value, brake status signal and fire monitoring signal of the quay crane equipment are collected through the wind speed sensor, brake status detector and fire monitoring device to obtain the original monitoring data; Classifying and arranging the original monitoring data according to the equipment number and the operating status to obtain a basic data group; According to the basic data set, a feature extraction module is used to analyze the relationship between wind speed and brake response, the corresponding relationship between equipment status and fire monitoring signals, and the coordination relationship between brakes to generate a feature tag sequence; Matching and analyzing the characteristic mark sequence with wind speed data, brake status data and fire monitoring data to form a device perception feature vector; The operating condition bearing capacity is calculated based on the equipment sensing feature vector in combination with the wind force level parameter and the brake state parameter to obtain the operating condition bearing index.

3. The intelligent fire and wind prevention linkage method based on port quay crane meteorological perception according to claim 1 is characterized in that: The step of calculating the protection margin coefficient based on the device perception feature vector and the working condition load index through a boundary mapping algorithm to generate the device operation toughness value includes: Extracting stable operation parameters, dynamic response parameters and safety threshold parameters from the device perception feature vector through a device bearing matrix extractor to generate a device capability attribute set; The working condition load index is segmented and matched according to different wind force levels by using a wind speed response associator to form a wind speed load correspondence table; Based on the equipment capability attribute set, a three-dimensional safety envelope surface is constructed, and the wind speed load corresponding table is mapped into the envelope surface to obtain a safe operation domain of the equipment; Calculating the boundary gradient of the safe operation domain of the equipment, and generating a protection margin coefficient in combination with the equipment operation status and the braking response time; The protection margin coefficient is adaptively matched with the real-time monitoring data, the stable operation parameters and emergency response parameters of the equipment are calculated, and the equipment operation toughness value is obtained.

4. The intelligent fire and wind prevention linkage method based on port quay crane meteorological perception according to claim 1 is characterized in that: Based on the equipment operation resilience value, the real-time monitoring data is correlated and analyzed to form a wind-fire coupling risk index and a disaster cascade impact degree, including: Extracting wind speed monitoring signals, brake status signals and fire warning signals from the real-time monitoring data through a risk identification unit to generate a wind and fire monitoring feature group; Using a protection level evaluator to perform state mapping on the equipment operation toughness value to form an equipment protection level sequence; Cross-matching the wind and fire monitoring feature group with the equipment protection level sequence according to the wind and fire coupling rule to obtain a risk-related feature chain; Analyzing the transfer relationship of the risk-related feature chain through a risk transfer evaluator to generate a wind-fire coupling risk index; Based on the temporal variation trend of the wind-fire coupling risk index, a disaster spreading situation map is constructed to form the disaster cascade impact degree.

5. The intelligent fire and wind prevention linkage method based on port quay crane meteorological perception according to claim 1 is characterized in that: The calculating of the operation capability prediction value and outputting the control response matching degree according to the wind-fire coupling risk index and the disaster cascade impact degree includes: Separating wind and fire prevention characteristic components from the wind-fire coupling risk index through a risk linkage decoupling unit to generate an operation risk characteristic chain; Using a disaster situation analyzer, the disaster cascade impact is expanded according to a brake response sequence to form a disaster evolution flow chart; According to the operation risk characteristic chain and the disaster evolution flow chart, an automatic operation tolerance determination matrix is ​​constructed to obtain the safety characterization parameters of the operation area; Mapping the safety characterization parameters of the operation area to the real-time equipment state space to generate an operation capability prediction value; Performing three-dimensional vector decomposition on the predicted working capacity value, extracting braking association features, operating situation features and control response features, and forming a multi-dimensional control coordination sequence; Control signal fitting and reconstruction is performed according to the multi-dimensional control coordination sequence, and a control response matching degree is output.

6. The intelligent fire and wind prevention linkage method based on port quay crane meteorological perception according to claim 1 is characterized in that: The step of adjusting the protection strategy adaptation coefficient according to the control response matching degree and feeding back the execution result to the device perception feature vector includes: The control response matching degree is signal-splitting performed by a control response parser to generate a brake control feature chain and a fire protection feature chain; Mapping the braking control feature chain and the fire protection feature chain to the equipment operation space using a control effectiveness evaluator to form a protection control mapping matrix; Extract key control nodes according to the protection control mapping matrix, construct a wind-fire linkage response map, and obtain a strategy adjustment sequence; The strategy adjustment sequence is segmented and matched according to the equipment operation status to generate a protection strategy adaptation coefficient; Extracting a state feedback component from the protection strategy adaptation coefficient through a response feature analyzer to form a state update feature group; The state update feature group is reconstructed according to the feature mapping relationship and fed back to the device perception feature vector.

7. The intelligent fire and wind prevention linkage method based on port quay crane meteorological perception according to claim 6 is characterized in that: The step of performing segmented matching on the strategy adjustment sequence according to the device operation status to generate a protection strategy adaptation coefficient includes: Decomposing the strategy adjustment sequence in time series by a state interval divider to obtain a risk protection segment and a fire protection segment; Using an operating condition feature extractor to separate a basic operating condition signal and a disturbance operating condition signal from the equipment operation state to form an operating condition feature spectrum; According to the timestamp information of the risk protection section and the fire protection section, a protection timing mapping table is constructed to obtain a protection priority sequence; Cross-validating the protection priority sequence with the operating condition characteristic spectrum to generate a device control response chain; Performing reliability evaluation on the device control response chain through a strategy coordination analyzer to form a protection execution sequence; The protection execution sequence is reconstructed into a strength value to generate a protection strategy adaptation coefficient.

8. An intelligent fire and wind prevention linkage system based on port quayside bridge meteorological perception, used to implement the intelligent fire and wind prevention linkage method based on port quayside bridge meteorological perception as described in any one of claims 1 to 7, characterized in that: The intelligent fire and wind prevention linkage system based on port quay crane meteorological perception includes: The acquisition module is used to collect the operation data of the quay crane equipment through the multi-dimensional sensing unit, build the equipment perception feature vector based on the equipment status record, and calculate the working condition load index; A calculation module, used to calculate the protection margin coefficient according to the device perception feature vector and the working condition load index through a boundary mapping algorithm to generate an equipment operation toughness value; A correlation module, used to perform correlation analysis on the real-time monitoring data based on the equipment operation resilience value to form a wind-fire coupling risk index and a disaster cascade impact degree; An output module, used to calculate the operation capacity prediction value and output the control response matching degree according to the wind-fire coupling risk index and the disaster cascade impact degree; The feedback module is used to adjust the protection strategy adaptation coefficient according to the control response matching degree, and feed back the execution result to the device perception feature vector.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and is characterized in that when the processor executes the computer program, the intelligent fire and wind prevention linkage method based on port quay crane meteorological perception as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the processor executes the intelligent fire and wind prevention linkage method based on port quay crane meteorological perception as described in any one of claims 1 to 7.

Images