A method and apparatus for analyzing and alerting on production data in a shipbuilding process

Abstract

The application relates to the technical field of data processing, and discloses a shipbuilding process production data analysis and alarm method and device, wherein the method comprises the following steps: performing preliminary analysis on production data collected in a shipbuilding process according to a preset primary safety production rule to generate primary alarm information; performing secondary intelligent analysis on the production data and the primary alarm information according to a preset secondary safety production rule to generate secondary alarm information when an analysis result meets a preset condition; and generating a safety production alarm information tree according to the primary alarm information and the secondary alarm information to visually display an accident evolution process. The technical scheme provided by the application can change from single-dimensional monitoring to multi-dimensional coupling early warning, and can provide an intelligent safety production alarm with an accident evolution visual view, so that the technical effect of intelligently changing from passive and discrete monitoring to active and accurate prevention and control of safety risks in a shipbuilding complex scene is achieved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method and apparatus for alarming production data analysis during shipbuilding process. Background Technology

[0002] Shipbuilding, as a complex systems engineering project, presents a high-risk working environment characterized by confined space, multi-level intersections, high temperatures and humidity, and numerous toxic and harmful gases. This means that the safety of workers depends not only on their own physiological functions but also on the dynamic influence of on-site environmental factors. However, existing safety monitoring technologies primarily rely on physiological monitoring based on fixed thresholds and independent environmental video surveillance. This traditional approach suffers from significant technical bottlenecks in practical applications: First, the universal threshold setting ignores individual differences among workers, leading to a high false alarm rate in a "one-size-fits-all" alarm mechanism, severely disrupting normal production order. Second, there is a severe "data silo" phenomenon between personnel physiological data and environmental parameters; the system lacks in-depth analysis of the "human-environment" coupling relationship, making it impossible to accurately determine whether physiological abnormalities are caused by personal illness or adverse environmental conditions, hindering scientific emergency decision-making. Finally, existing systems lack the ability to visually reconstruct the accident evolution process; discrete log records make post-accident tracing and review extremely difficult, failing to clearly reconstruct the logical chain of the accident.

[0003] Therefore, existing technologies urgently need an intelligent safety production alarm method that can combine individual personnel characteristics with on-site environmental parameters to achieve the transformation from "single-dimensional monitoring" to "multi-dimensional coupled early warning" and provide a visual view of accident evolution, so as to realize the intelligent transformation of safety risks in complex shipbuilding scenarios from passive discrete monitoring to proactive and precise prevention and control. Summary of the Invention

[0004] This application provides a method and device for analyzing and alarming production data during shipbuilding. It achieves the technical effect of combining individual personnel characteristics with on-site environmental parameters to realize the transformation from "single-dimensional monitoring" to "multi-dimensional coupled early warning" and provide a visualized view of accident evolution. It realizes the technical effect of transforming the intelligent control of safety risks in complex shipbuilding scenarios from passive discrete monitoring to proactive and precise prevention and control.

[0005] To achieve the above objectives, the main technical solutions adopted in this application include: In a first aspect, embodiments of this application provide a method for alarming production data analysis during shipbuilding, the method comprising: According to the preset safety production rules, the production data collected during the ship construction process is preliminarily analyzed to generate an alarm message, which is then sent to the alarm equipment and safety officer at the production station. According to the preset secondary safety production rules, a secondary intelligent analysis is performed by combining the production data and the primary alarm information. If the analysis results meet the preset conditions, a secondary alarm information is generated and sent to the alarm device and the safety officer. Based on the primary alarm information and the secondary alarm information, a safety production alarm information tree is generated to visualize the accident evolution process.

[0006] In one implementation, the production data includes personnel data, equipment data, and environmental data; wherein, The personnel data includes employee number, name, weight, height, heart rate, blood pressure, blood oxygen saturation, limb behavior, spatial positioning, horizontal movement speed, and vertical movement speed. The equipment data includes process station, equipment name, equipment operating parameters, production plan, production object, and quantity of finished products; The environmental data includes production area, process station, temperature, humidity, wind speed, metal dust, welding fumes, noise, paint mist, and harmful gases.

[0007] In one implementation, the step of performing preliminary analysis on production data collected during the shipbuilding process according to preset safety production rules and generating an alarm message includes: Extract personnel dynamic data from the production data; Based on the personnel safety rules in the aforementioned safety production rules, the dynamic data of the personnel is analyzed to generate corresponding alarm information.

[0008] In one implementation, the step of analyzing the personnel dynamic data based on the personnel safety rules in the primary safety production rules to generate corresponding primary alarm information includes: The static characteristic parameters of the personnel are obtained, and based on the preset physiological characteristic model, the initial blood pressure state curve and the initial heart rate state curve for the personnel are generated. Based on the initial blood pressure curve and the initial heart rate curve, a range of personalized safety data suitable for the individual is defined. Compare the personnel dynamic data in the production data with the corresponding range of personalized safety data; When the personnel dynamic data exceeds the range of the personalized security data, an alarm message is generated.

[0009] In one implementation, the step of performing secondary intelligent analysis based on preset secondary safety production rules, combining the production data and the primary alarm information, and generating secondary alarm information under preset conditions, includes: In response to the alarm information, the personalized safety data range and current personnel dynamic data on which the alarm information was generated are obtained, and environmental operation parameters that are spatially and temporally related to the personnel dynamic data are extracted from the production data. The personalized safety data range, the personnel dynamic data and the environmental operation parameters are fused together to construct a secondary analysis feature vector set. Based on the secondary analysis feature vector set, the correlation between the extent to which the personnel dynamic data exceeds the range of the personalized safety data and the environmental operation parameters is determined through the secondary safety production rules, thereby generating a comprehensive safety risk value; The comprehensive safety risk value is compared with a preset intervention threshold. If the comprehensive safety risk value exceeds the intervention threshold, a secondary alarm message containing the risk level, recommended handling measures, and related environmental parameters is generated.

[0010] In one implementation, the step of determining the correlation between the extent to which the personnel dynamic data exceeds the range of the personalized safety data and the environmental operation parameters based on the secondary analysis feature vector set and the secondary safety production rules, and generating a comprehensive safety risk value, includes: Based on the set of secondary analysis feature vectors, the deviation of the personnel dynamic data from the baseline in the range of personalized safety data is calculated, and the deviation is mapped to a preset physiological risk level. The environmental operation parameters are extracted from the set of secondary analysis feature vectors, and an independent risk assessment is performed on the environmental operation parameters according to the preset environmental safety rules to generate the corresponding environmental risk level. The coupling rule set in the secondary safety production rules is invoked to associate and match the physiological risk level with the environmental risk level to determine the risk amplification coefficient; Based on the risk amplification coefficient and combined with the initial weights of the physiological risk level and the environmental risk level, a final comprehensive safety risk value is generated through weighted calculation.

[0011] In one implementation, generating a safety production alarm information tree based on the primary alarm information and the secondary alarm information to visually display the accident evolution process includes: Using the alarm information as the starting point, the personnel identifier, alarm time, and initial physiological abnormality type in the alarm information are extracted and encapsulated as the root node of the safety production alarm information tree to establish the individual triggering source of the alarm event. Based on the association identifier carried in the secondary alarm information, secondary alarm records that match the root node in time and space are retrieved, and secondary alarm information that represents the risk of environmental coupling is used as a child node and attached to the root node to form a parent-child association link. The personalized safety data range used to generate the first alarm information and the environmental operation parameters used to generate the second alarm information are respectively mapped to the attribute fields of the root node and the child node. The root node, child nodes, and attribute fields are serialized and encapsulated to generate the safety production alarm information tree for visual display of the accident evolution process.

[0012] In one embodiment, the method further includes: Based on the anomaly type in the primary alarm information and the associated environmental parameters in the secondary alarm information, a pre-prepared emergency response plan is matched. The matched emergency response plan will be sent to the safety officer as a response suggestion.

[0013] In one embodiment, the alarm device is an audible and visual alarm installed at the production site, or a smart terminal carried by personnel.

[0014] Secondly, embodiments of this application provide a shipbuilding process production data analysis and alarm device, the device comprising: The primary alarm unit is used to perform preliminary analysis on the production data collected during the shipbuilding process according to the preset primary safety production rules, generate primary alarm information, and send the primary alarm information to the alarm equipment and safety officer at the production workstation. The secondary alarm unit is used to perform secondary intelligent analysis based on preset secondary safety production rules, combined with the production data and the primary alarm information, generate secondary alarm information under the condition that the analysis results meet preset conditions, and send the secondary alarm information to the alarm device and the safety officer. The information tree generation unit is used to generate a safety production alarm information tree based on the primary alarm information and the secondary alarm information, so as to visualize the evolution process of the accident.

[0015] Thirdly, embodiments of this application provide a computer device, including: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes these computer instructions to perform the aforementioned method for analyzing and alarming production data during the shipbuilding process.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer instructions, which are used to cause a computer to execute the above-described method for analyzing and alarming production data during the shipbuilding process.

[0017] In one or more preferred embodiments, the shipbuilding process production data analysis and alarm method provided by this application utilizes personalized thresholds based on individual physical conditions to replace the traditional one-size-fits-all standard, achieving millisecond-level accurate identification of physiological abnormalities in personnel. This eliminates the interference of high false alarm rates caused by individual differences at the source, ensuring the accuracy of risk perception. Secondly, it breaks through the limitations of single-dimensional monitoring by deeply integrating personnel dynamics and environmental parameters, intelligently quantifying the comprehensive risks under the human-environment coupling effect, and elevating safety analysis from simple state monitoring to the level of cause diagnosis, providing a scientific basis for decision-making to prevent the evolution of accidents. Finally, it innovatively constructs a safety production alarm information tree, reconstructing discrete alarm data into a visualized causal logic chain, clearly reproducing the complete spatiotemporal trajectory of an accident evolving from a single physiological trigger to a complex environmental amplification. This not only achieves transparent tracing of the accident process but also provides intuitive and reliable data support for subsequent safety procedure optimization and responsibility determination, thereby promoting a qualitative leap in safety management from passive post-event accountability to proactive pre-event prevention. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a method for analyzing and alarming production data during shipbuilding processes, provided as an embodiment of this application; Figure 2 A flowchart of step S1 provided in the embodiments of this application; Figure 3 A flowchart of step S13 provided in an embodiment of this application; Figure 4 A flowchart of step S3 provided in the embodiments of this application; Figure 5 A flowchart of step S33 provided in an embodiment of this application; Figure 6 A flowchart of step S5 provided in an embodiment of this application; Figure 7 A block diagram of a shipbuilding process production data analysis and alarm device provided in this application embodiment; Figure 8 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] Shipbuilding is a complex systems engineering project with a working environment characterized by confined space, multiple interconnected areas, high temperature and humidity, numerous toxic and harmful gases, and high work intensity. In this high-risk industry, the safety of workers depends not only on their individual physical condition but also heavily on on-site environmental factors (such as oxygen deficiency in confined spaces, high-temperature welding fumes, and the risks of working at heights). Traditional safety management mainly relies on manual inspections and simple threshold alarms, which are insufficient to cope with the complex and ever-changing on-site environment, resulting in a situation where "what can be seen cannot be managed, and what can be managed cannot be seen."

[0022] Currently, the industry mainly uses the following two technical means for safety monitoring during the shipbuilding process: 1. Physiological monitoring technology based on fixed thresholds: Existing smart wearable devices (such as smart bracelets and smart safety helmets) are typically used to collect physiological data such as workers' heart rate, blood pressure, and blood oxygen levels. When the monitored values ​​exceed preset general industry standard thresholds (e.g., heart rate > 120 beats / minute), the system will trigger an alarm.

[0023] 2. Independent environmental monitoring and video surveillance technology: Environmental sensors deployed on-site are used to monitor parameters such as temperature, humidity, and concentration of toxic gases; at the same time, a video surveillance system is used to observe the behavior and posture of personnel (such as falling or entering restricted areas).

[0024] While the aforementioned technologies have improved security management to some extent, the following significant technical problems still exist in practical applications, making it difficult to meet the needs of refined security management: Defect 1: The alarm threshold is applied in a "one-size-fits-all" manner, resulting in a high false alarm rate.

[0025] Existing physiological monitoring technologies typically use uniform, fixed thresholds, ignoring individual differences among workers (such as physical condition and underlying medical conditions). For example, a heart rate of 120 beats per minute might be normal for a young, healthy welder; however, for a middle-aged or elderly worker with a history of hypertension, the same heart rate could be dangerously high. This lack of personalized consideration leads to numerous invalid alarms (false alarms) or missed alarms, disrupting normal production and reducing the reliability of safety systems.

[0026] Defect 2: The data silo phenomenon is serious, and there is a lack of "human-environment" coupling analysis.

[0027] Existing systems often analyze "personnel physiological data" and "environmental operational parameters" separately. The system cannot determine whether a person's physiological abnormality is caused solely by illness or induced by harsh environments (such as high temperatures or oxygen deficiency). This isolated alarm mechanism (reporting illness without specifying the cause) prevents safety officers from making accurate emergency decisions and hinders efforts to prevent accidents from escalating at their source.

[0028] Defect 3: It is difficult to trace the source of the accident and lacks a visual evolution view.

[0029] Following an accident, existing data records are typically discrete, unstructured log files. There is a lack of a visualization tool that can intuitively show the evolution of the accident from "physiological abnormality triggering" to "environmental risk coupling." This makes post-accident review and liability determination difficult, and it is impossible to clearly reconstruct the logical relationships between the elements of "people, machines, materials, methods, and environment" in the accident.

[0030] In summary, existing technologies urgently need an intelligent safety production alarm method that can combine individual personnel characteristics with on-site environmental parameters to transform from "single-dimensional monitoring" to "multi-dimensional coupled early warning" and provide a visualized view of accident evolution, so as to realize the intelligent transformation of safety risks in complex shipbuilding scenarios from passive discrete monitoring to proactive and precise prevention and control.

[0031] According to an embodiment of this application, an embodiment of a method for alarming production data analysis during ship construction is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0032] This embodiment provides a method for alarming production data analysis during shipbuilding. Figure 1 A flowchart of a production data analysis and alarm method for shipbuilding process provided in this application embodiment is shown below. Figure 1 As shown, the process includes the following steps: Step S1: Based on the preset safety production rules, perform preliminary analysis on the production data collected during the shipbuilding process, generate an alarm message, and send the alarm message to the alarm equipment and safety officer at the production station.

[0033] Specifically, by using a set of safety production rules as a rapid filter, dynamic personnel data is accurately extracted from massive production data and compared in real time with personalized safety data ranges built based on individual physical conditions. Once a physiological indicator is detected to exceed the individual's tolerance threshold, an alarm is immediately triggered and pushed to the workstation terminal and the safety officer. This enables millisecond-level early warning and intervention in the initial stage of an accident (i.e., the period of simple physiological abnormality), effectively preventing individual health risks from turning into production safety accidents.

[0034] In one optional implementation, the production data includes personnel data, equipment data, and environmental data; wherein, Personnel data includes employee ID, name, weight, height, heart rate, blood pressure, blood oxygen saturation, limb behavior, spatial positioning, horizontal movement speed, and vertical movement speed; Equipment data includes process station, equipment name, equipment operating parameters, production plan, production object, and quantity of finished products; Environmental data includes production area, process station, temperature, humidity, wind speed, metal dust, welding fumes, noise, paint mist, and harmful gases.

[0035] In one alternative implementation, the alarm device is an audible and visual alarm installed at the production site, or a smart terminal carried by personnel.

[0036] Step S3: Based on the preset secondary safety production rules, a secondary intelligent analysis is performed by combining production data and primary alarm information. If the analysis results meet the preset conditions, secondary alarm information is generated and sent to the alarm equipment and safety officer.

[0037] Specifically, based on the secondary safety production rules, the dynamic data of personnel and environmental operation parameters are deeply integrated. By calculating the correlation between physiological deviation and environmental risk, the comprehensive safety risk value under the human-environment interaction is intelligently identified. Only when this coupled risk exceeds the preset intervention threshold will a secondary alarm message containing specific handling suggestions be triggered, thereby achieving precise prevention and scientific decision-making for the evolution of potential accidents.

[0038] Step S5: Based on the primary alarm information and the secondary alarm information, generate a safety production alarm information tree to visualize the accident evolution process.

[0039] Specifically, the root node of the alarm information is used to establish the triggering source of individual physiological abnormalities, and the secondary alarm information is used as a child node to attach the evolutionary branch of environmental coupling risks. By constructing a safety production alarm information tree, the originally discrete alarm data is linked into a clear "physiological trigger-environmental amplification" causal chain. This allows safety managers to clearly understand the complete spatiotemporal logic of the evolution of an accident from "single point abnormality" to "compound risk" through a visualized tree topology diagram.

[0040] In an optional implementation, the method further includes: matching a pre-prepared emergency response plan based on the anomaly type in the primary alarm information and the associated environmental parameters in the secondary alarm information; The matched emergency response plan will be sent to the safety officer as a response suggestion.

[0041] Specifically, in this embodiment, an emergency response plan knowledge base is preset. This knowledge base stores multiple standard response plans. j Each solution is associated with a specific "applicable physiological abnormality type" and "applicable environmental constraints." After generating primary and secondary alarm information, feature extraction and vectorization are performed first: the abnormality type in the primary alarm information (such as "precursor to heatstroke") is extracted and mapped to a semantic feature vector V. type Extract the associated environmental parameters (such as "temperature 40℃", "humidity 80%", "enclosed space") from the secondary alarm information and quantify them into an environmental feature vector V. env By combining the two methods, a comprehensive query vector V for retrieval is constructed. query V query =λ1·V type +λ2·V env λ1 and λ2 are weighting coefficients, and λ1 > λ2 usually indicates that physiological abnormalities are the primary factor triggering treatment, while environmental parameters are the corrective factors.

[0042] To find the most suitable solution from the knowledge base, the comprehensive query vector V is calculated. query With each pre-stored solution vector Vplan in the knowledge base j The similarity between the two scenarios is measured using a cosine similarity algorithm. The calculation formula is as follows: Among them, Sim j q represents the similarity score between the current scene and the j-th pre-stored solution. i and p ji These represent the i-th dimension component of the vector.

[0043] Traverse the knowledge base and select the solution with the highest similarity score as the emergency response plan for the target. target : For example, if the first alarm message is tachycardia and the second alarm message shows an ambient temperature of 40℃, after calculation, it is found that the similarity with the "Emergency Plan for Heatstroke in High Temperature Operations" in the solution library is 0.95, while the similarity with the "Emergency Plan for Sudden Heart Attack" is only 0.60. Therefore, the "Emergency Plan for Heatstroke in High Temperature Operations" is selected.

[0044] This embodiment provides a production data analysis and alarm method for shipbuilding processes. It replaces the traditional one-size-fits-all standard with personalized thresholds based on individual physical conditions, achieving millisecond-level accurate identification of physiological abnormalities in personnel. This eliminates the high false alarm rate interference caused by individual differences at the source, ensuring the accuracy of risk perception. Secondly, it breaks through the limitations of single-dimensional monitoring by deeply integrating personnel dynamics and environmental parameters, intelligently quantifying the comprehensive risks under the human-environment coupling effect. This elevates safety analysis from simple state monitoring to the level of causal diagnosis, providing a scientific basis for preventing accident evolution. Finally, it innovatively constructs a safety production alarm information tree, reconstructing discrete alarm data into a visualized causal logic chain. This clearly reproduces the complete spatiotemporal trajectory of an accident evolving from a single physiological trigger to a complex environmental amplification. This not only achieves transparent tracing of the accident process but also provides intuitive and reliable data support for subsequent safety procedure optimization and responsibility determination, thereby promoting a qualitative leap in safety management from passive post-event accountability to proactive pre-event prevention.

[0045] Figure 2 The flowchart for step S1 provided in the embodiments of this application may include the following steps: Step S11: Extract personnel dynamic data from the production data.

[0046] Specifically, from the vast amount of IoT data, surveillance video streams, and sensor networks at the shipbuilding site, dynamic data characterizing the real-time status of personnel is extracted through data cleaning, feature recognition, and correlation matching. Production data includes not only environmental parameters (such as temperature, humidity, and noise), but also personnel location information, physiological indicators, behavioral postures, and equipment interaction data. The system collects this data in real time through multi-source sensing devices deployed at the work site (such as UWB positioning base stations, smart wearable devices, and high-definition cameras) and transmits it to the central processing unit.

[0047] Specifically, the extraction process includes two stages: data preprocessing and feature extraction. In the data preprocessing stage, the raw data is denoised, standardized in format, and timestamp aligned to eliminate data distortion caused by transmission delays or equipment errors. For example, for heart rate sensor data obtained from a smart safety helmet, a moving average filtering algorithm is used to remove power frequency interference, ensuring data smoothness and reliability. In the feature extraction stage, preset data parsing rules are used to identify and separate personnel dynamic data from the preprocessed data stream. Personnel dynamic data includes at least real-time heart rate, real-time blood pressure, blood oxygen saturation, body surface temperature, three-dimensional spatial coordinates, movement speed, and posture angles (such as tilt angle and fall status).

[0048] To improve the accuracy of data extraction, this embodiment also incorporates personnel identification technology. The system reads the unique identifier (ID) of the wearable device and binds the extracted dynamic data with specific personnel information, forming a "personnel-dynamic data" mapping table. This allows subsequent analysis steps to perform precise security assessments targeting specific individuals, rather than simply analyzing general group data. For example, when receiving a set of heart rate data with the ID "W00123", the system can immediately identify that the data belongs to the welder with the ID "W00123" and include him in that person's real-time dynamic data stream, laying the foundation for further rule analysis.

[0049] Step S13: Based on the personnel safety rules in the safety production rules, analyze the personnel dynamic data and generate corresponding alarm information.

[0050] Specifically, the system invokes a pre-stored primary safety production rule base, particularly a subset of rules specifically designed for personnel safety, to perform real-time analysis and logical reasoning on extracted personnel dynamic data. These primary safety production rules are pre-defined based on safety production standards, industry best practices, and internal enterprise safety management systems, and are stored in the system database in the form of logical expressions or decision trees. Each rule defines the safety thresholds or behavioral norms that personnel should adhere to in a specific work environment.

[0051] The specific analysis process is as follows: The extracted personnel dynamic data is used as input variables and compared and calculated in the corresponding safety rule logic. For example, for the safety rule of "monitoring the vital signs of personnel working at heights," the following logical conditions are set: if (real-time heart rate > 120 beats / min) OR (blood oxygen saturation < 90%) OR (posture angle display showing continuous tilt for more than 30 seconds), then it is determined to be an abnormal state. The extracted dynamic data stream is monitored in real time. Once it is found that the data at a certain moment meets any one or more of the above logical conditions, it is determined that the person's current state violates the personnel safety rules.

[0052] Upon determining an abnormal state, an alarm mechanism is immediately triggered, generating a corresponding primary alarm message. This primary alarm message is the first and most basic warning signal generated by the system for this abnormal event, designed to notify on-site management personnel or the security monitoring center as soon as possible so that timely intervention measures can be taken. The data structure of this alarm message is carefully designed to ensure the integrity and readability of the information. A primary alarm message includes at least the following fields: alarm type (e.g., "physiological abnormality," "location intrusion," or "fall alarm"), alarm level (based on preset severity rules, such as "Level 1 Emergency," "Level 2 Warning"), the ID of the specific person who triggered the alarm, the dynamic data value that triggered the alarm (e.g., "heart rate 135 beats / min"), the timestamp of the alarm occurrence, and the geographical coordinates of the alarm's location.

[0053] To enhance the intuitiveness and operability of alarms, alarm description text can be automatically generated. For example, when it is detected that the oxygen concentration in a confined space is below the safe level and the person is stationary, the generated alarm message might read: "Warning: Worker number W00456 has been unresponsive for an extended period in compartment A3-02, and the ambient oxygen content is low. Please proceed to check immediately." This alarm message is quickly communicated to relevant personnel through various means, such as audible and visual alarms, mobile terminal push notifications, or pop-ups on monitoring screens, effectively preventing the occurrence or escalation of safety accidents.

[0054] This embodiment significantly improves safety management by real-time monitoring and analysis of personnel dynamic data at the shipbuilding site. Multi-source sensing devices (such as UWB positioning base stations, smart wearable devices, and high-definition cameras) are used to extract real-time physiological and behavioral dynamic data of personnel. After preprocessing steps such as noise reduction, format standardization, and feature extraction, the accuracy and reliability of the data are ensured. Then, based on a pre-stored primary safety production rule base, this dynamic data is analyzed. Once an anomaly is detected (such as excessively high heart rate or excessively low blood oxygen saturation), detailed alarm information is immediately generated and quickly notified to on-site management personnel via audible and visual alarms and mobile terminals. This series of processes not only enables rapid identification and response to potential safety hazards but also enhances the precise monitoring of individual workers, thereby effectively reducing the probability of accidents and ensuring operational safety.

[0055] Figure 3 The flowchart for step S13 provided in the embodiments of this application may include the following steps: Step S131: Obtain the static characteristic parameters of the personnel, and generate the initial blood pressure state curve and initial heart rate state curve for the personnel based on the preset physiological characteristic model.

[0056] Specifically, this step aims to establish a digital physiological twin baseline for every worker entering the shipbuilding site. Unlike traditional techniques that use uniform industry standards (such as a uniform rule that the heart rate must not exceed 100 beats / minute), this step fully considers individual differences (such as age, physical condition, and medical history). First, the static feature parameter vector U is obtained through the personnel management database. static Static characteristics include at least: age (A), sex (G), body mass index (BMI), medical history labels (H, such as history of hypertension), and basal metabolic rate.

[0057] Based on static feature parameters, a preset physiological feature model is invoked to generate an initial state curve. In this embodiment, the physiological feature model adopts a regression prediction model based on large-scale population data.

[0058] Taking the initial heart rate curve as an example, first calculate the individual's theoretical resting heart rate baseline value HR. base Based on physiological principles, age is negatively correlated with maximum heart rate, while body mass index (BMI) is positively correlated with cardiac load. The following calculation formula is constructed: HR base =α0+α1·(220-A)+α2·BMI+α3·H score +ε1 Where A represents the age of the person; BMI represents the body mass index; H score The risk score is determined by medical history (e.g., 0 for no medical history, 1.2 for a history of hypertension); α0, α1, α2, α3 are the weight coefficients obtained from model training; ε1 is the correction error term.

[0059] Similarly, the baseline value SBP of the initial blood pressure status curve (taking systolic blood pressure SBP as an example) base SBP can be generated using the following formula: base =β0+β1·A+β2·BMI+β3·G+ε2, where β0,β1,β2,β3 are the weight coefficients obtained from model training; ε2 is the correction error term.

[0060] It should be noted that the initial state curve is not a straight line, but a dynamic curve that changes with time (e.g., working hours t). Considering that shipbuilding operations typically involve an 8-hour workday, the physiological performance of the human body differs in the initial, middle, and fatigue stages of the work. Therefore, the initial heart rate curve HR... init (t) can be represented as: HR init (t)=HR base ·(1+k work ·f(t)), where f(t) is the fatigue growth function based on working time t, k work This is the load factor based on the intensity of the job.

[0061] Step S133: Based on the initial blood pressure status curve and the initial heart rate status curve, the range of personalized safety data for the suited personnel is defined.

[0062] Specifically, after obtaining the initial curve, a dynamic tolerance mechanism is introduced to define a personalized secure data range that is both safe and not overly sensitive. Specifically, the personalized secure data range is a set of intervals R that varies over time. safe (t)=[Val min (t),Val max (t)]. The range is defined based on the initial curve plus a personalized safety threshold Δ. To accommodate the physiological fluctuations of different individuals (e.g., young people have faster heart rate recovery, so the fluctuation range can be set larger; older people have a higher risk of blood pressure fluctuations, so the range needs to be set more strictly), this embodiment uses the standard deviation adaptive method to determine the boundary. The calculation formula is as follows: Val min (t)=Val init (t)-n·σ personal Val max (t)=Val init (t)+n·σ personal Val init (t) represents the value of the initial curve generated in step S131 at time t (e.g., HR). init (t) or SBP base ); σ personal is the standard deviation of physiological indicators in the person's historical health data (if no historical data is available, the population mean standard deviation is used); n is the safety factor, which is usually between 2 and 3 (corresponding to a 95% to 99% confidence interval).

[0063] For example: For a 25-year-old welder with a theoretical resting heart rate of 75, considering the high level of concentration required for welding, their individualized safe range can be set to [60, 110]. For a 50-year-old structural assembler with a mild history of hypertension, based on their initial blood pressure curve, their individualized safe range for systolic blood pressure might be set to [110, 145], rather than the universal [90, 140]. This classification effectively avoids false positive alarms (i.e., normal physiological fluctuations being mistakenly reported as abnormal).

[0064] Step S135: Compare the personnel dynamic data in the production data with the corresponding personalized safety data range.

[0065] Specifically, real-time dynamic data streams of personnel are collected through smart wearable devices (such as smart bracelets and smart helmets). real(t), this data stream contains real-time heart rate HR real (t) and real-time blood pressure BP real (t). D real (t) is mapped in real time to the interval R generated in step S133. safe The comparison is performed in (t). To eliminate false alarms caused by instantaneous jumps due to sensor noise, this embodiment uses a sliding window integration method. The anomaly detection function J(t) is defined as follows: Wherein: T w 1 is the preset time window (e.g., 30 seconds); II() is an indicator function that takes the value 1 when the data is out of range, and 0 otherwise.

[0066] Step S137: If the personnel dynamic data exceeds the range of personalized security data, generate an alarm message.

[0067] Specifically, when the value of the anomaly detection function J(t) exceeds the preset trigger ratio γ (e.g., γ=0.8, meaning that 80% of the time data exceeds the limit within 30 seconds), the person is determined to be in an abnormal physiological state, and an alarm message is generated. The data structure of an alarm message includes at least the following: Alarm ID: a unique identifier; Personnel ID: the worker number that triggered the alarm; Anomaly type: such as "persistent tachycardia" or "hypertensive crisis"; Exceeded value: the actual physiological value at the time of triggering; Timestamp: the time the alarm occurred.

[0068] This embodiment acquires the static characteristic parameters of workers and, based on a preset physiological characteristic model, generates initial blood pressure and heart rate curves for each individual. This personalized modeling method improves the accuracy of health monitoring and ensures the relevance of the monitoring data. Furthermore, it defines personalized safety data ranges tailored to each individual, effectively reducing false alarm rates and avoiding false positive alarms caused by uniform standards. By monitoring workers' physiological states in real time and dynamically adapting to changes under different job types and work intensities, potential health risks can be identified promptly, enhancing workplace safety. In addition, this precise health monitoring improves employee work efficiency and satisfaction, helps reduce absenteeism due to health problems, and ultimately optimizes the overall working environment.

[0069] Figure 4 The flowchart for step S3 provided in the embodiments of this application may include the following steps: Step S31: In response to an alarm message, obtain the personalized safety data range and current personnel dynamic data on which the alarm message was generated, and extract the environmental operation parameters that are spatially and temporally related to the personnel dynamic data from the production data. Then, integrate the personalized safety data range, personnel dynamic data and environmental operation parameters to construct a secondary analysis feature vector set.

[0070] Specifically, in response to an alarm (e.g., an alarm about abnormal heart rate), data backtracking and correlation extraction are first performed. The personalized safety data range upon which the alarm was based (e.g., the normal heart rate range for that specific worker [50, 110]) and the current dynamic data of the worker at the moment the alarm was triggered (e.g., real-time heart rate of 125 bpm) are immediately obtained. Based on the timestamp t of the production data and the worker's location coordinates (x, y, z), environmental operation parameters highly correlated with the worker in time and space are retrieved from massive production data. These parameters include, but are not limited to: real-time temperature T, humidity H, noise level N, and toxic gas concentration G of the work area. After normalizing the above three types of data, they are fused to construct an n-dimensional quadratic analysis feature vector set V. sec : Among them, D curr For current personnel dynamic data, Val min (t) and Val max (t) represents the upper and lower limits of the personalized safety range, respectively. This fusion approach ensures that subsequent analyses focus not only on the numerical values ​​themselves, but also on their deviation from the individual baseline.

[0071] Step S33: Based on the secondary analysis feature vector set, the correlation between the extent to which the dynamic data of personnel exceeds the range of personalized safety data and the environmental operation parameters is determined through secondary safety production rules, and a comprehensive safety risk value is generated.

[0072] Specifically, by using a set of secondary analysis feature vectors, the deviation of personnel's physiological indicators is correlated with the on-site environmental operation parameters in the same spatiotemporal dimension. Through secondary safety production rules, it is possible to identify whether there is a causal coupling between the two (for example, to determine whether a surge in heart rate is induced by a high temperature and high humidity environment). This transforms a simple physiological overshoot into a comprehensive safety risk value that includes the superimposed effects of the environment, thereby accurately determining whether the current danger is due to an individual's sudden illness or an escalation of operational risks caused by environmental deterioration.

[0073] Step S35: Compare the comprehensive safety risk value with the preset intervention threshold. If the comprehensive safety risk value exceeds the intervention threshold, generate secondary alarm information including risk level, recommended handling measures and related environmental parameters.

[0074] Specifically, the calculated comprehensive security risk value R final With the preset intervention threshold Th intervene Perform a comparison. If R final ≤Th intervene Maintain monitoring status or only log; if R final >Th intervene If the anomaly is detected, it is determined that the anomaly constitutes a substantial security threat and requires immediate intervention. A secondary alarm message is automatically generated. This message is no longer a simple "heart rate abnormality," but a structured data packet containing multi-dimensional information: Risk level: According to R final Numerical range mapping (such as "Level 1 Emergency" and "Level 2 Warning").

[0075] Recommended action: Based on rule engine matching, such as "immediately stop high-altitude operations", "turn on area ventilation equipment", or "call medical assistance".

[0076] Related environmental parameters: clearly indicate the environmental factors that lead to increased risk, such as "current area temperature 40°C, humidity 85%".

[0077] This embodiment acquires personalized safety data ranges and current personnel dynamic data, and extracts environmental and operational parameters related to these data in time and space, enabling precise identification of individual safety status. This personalized monitoring enhances sensitivity to changes in physiological conditions, facilitating early warnings and reducing potential risks. Simultaneously, correlation analysis with environmental factors makes risk assessment more comprehensive and scientific. Based on the constructed secondary analysis feature vector set, a comprehensive safety risk value is calculated and compared with a preset intervention threshold. When the risk value exceeds the threshold, a secondary alarm message containing the risk level, recommended handling measures, and related environmental parameters is automatically generated, thereby quickly activating the emergency response plan. This intelligent response mechanism significantly improves the efficiency and effectiveness of safety management, helping to protect personnel's lives and health.

[0078] Figure 5 The flowchart for step S33 provided in the embodiments of this application may include the following steps: Step S331: Based on the secondary analysis feature vector set, calculate the deviation of the personnel dynamic data from the baseline in the range of personalized safety data, and map the deviation to a preset physiological risk level.

[0079] Specifically, based on the constructed secondary analysis feature vector set, dynamic personnel data (denoted as X) is extracted. dynamic The baseline for personalized security data range (usually the mean M) base Or standard upper limit U limit The deviation δ of the personnel's dynamic data from the baseline is calculated.dev This deviation reflects the degree of abnormality in an individual's physiological indicators: Among them, Range safe For the width of the scope of personalized security data (i.e., Val) max (t)]-Val min (t), upper limit minus lower limit); M base This represents the average of the range of personalized security data.

[0080] Risk level mapping: A pre-set physiological risk mapping table is used. Based on the calculated deviation δ... dev This is mapped to a specific physiological risk level R. physio .For example: If 0 < δ dev If ≤0.50, then R physio =Low risk; If 0.5 < δ dev If R ≤ 1.0, then physio =Medium risk; If δ dev If R > 1.0, then physio =High risk.

[0081] Step S333: Extract environmental operation parameters from the set of secondary analysis feature vectors, and conduct independent risk assessments on the environmental operation parameters according to preset environmental safety rules to generate corresponding environmental risk levels.

[0082] Specifically, the set of environmental operation parameters {P} is extracted from the set of feature vectors in the quadratic analysis. env (e.g., temperature, dust, voltage, etc.) and conduct independent environmental risk assessments. Based on pre-defined environmental safety rules (usually according to industry safety standards), threshold comparisons are performed on each environmental parameter. For each environmental parameter P... i Calculate its corresponding environmental risk score Senv i For example, for a temperature T, if T>35℃ and T≤40℃, it is judged as "high temperature level 1" with a risk score of S1; if T>40℃, it is judged as "high temperature level 2" with a risk score of S2 (S2>S1).

[0083] By combining the risk scores of all environmental parameters, the final environmental risk level R is generated by taking the maximum value or using a weighted average method. env This step ensures that the danger of environmental factors is objectively quantified, without being directly affected by the current physiological state of the person.

[0084] Step S335: Invoke the coupling rule set in the secondary safety production rules, associate and match the physiological risk level with the environmental risk level, and determine the risk amplification coefficient.

[0085] Specifically, the physiological risk level R obtained in step S331 will be... physio The environmental risk level R obtained in step S333 env The data is input into a set of coupling rules for matching. This set incorporates expert experience and historical accident data. For example, the rule set defines that when a person is in a "high-risk" physiological state (such as tachycardia) and the environment is in a "high-temperature" state, the high-temperature environment will significantly accelerate the rate of physiological deterioration. This interaction produces a risk amplification effect of "1+1>2". Based on the matching results, a risk amplification coefficient α is determined, and this coefficient is normalized. For example, if both physiological and environmental conditions are high-risk, then α=1.5; if only one is high-risk, then α=1.0 (no amplification); if both are low-risk, then α=0.8 (risk offset or reduction).

[0086] Step S337: Based on the risk amplification coefficient and combined with the initial weights of physiological risk level and environmental risk level, the final comprehensive safety risk value is generated through weighted calculation.

[0087] Specifically, based on the above calculation results, the final comprehensive security risk value R is generated. final The initial weights for physiological risk and environmental risk are preset to W. p and W e (usually W) p +W e =1, for example W p =0.6,W e =0.4 (depending on the specific application scenario). The initial weighted result is corrected using a risk amplification factor α to reflect the coupling effect.

[0088] Among them, Score(R) physio ) and Score(R env These are the quantitative scores after converting the risk level (e.g., "high risk" = 100 points, "medium risk" = 60 points).

[0089] This embodiment, through real-time monitoring and early warning of personnel dynamic data, can promptly identify abnormalities in individual physiological states, thereby providing rapid health risk warnings. Secondly, by independently assessing environmental operational parameters, it ensures the scientific and reliable generation of environmental risk levels, thus improving the accuracy of risk assessment. Furthermore, coupling analysis of physiological risk levels and environmental risk levels can identify the interaction between the two, especially the amplification effect under high-risk conditions, thus providing a more comprehensive assessment of overall risk. Finally, by weighted calculation of the comprehensive safety risk value, considering both individual physiological risk and environmental factors, it provides a comprehensive safety risk assessment framework. This personalized safety management approach not only improves the targeting and effectiveness of management but also reduces the probability of accidents, promoting the intelligent and scientific development of safety production management.

[0090] Figure 6 The flowchart for step S5 provided in the embodiments of this application may include the following steps: Step S51: Taking an alarm message as the starting point, extract the personnel identification, alarm time and initial physiological abnormality type from the alarm message, encapsulate them as the root node of the safety production alarm information tree, and establish the individual triggering source of the alarm event.

[0091] Specifically, a single alarm message is used as the logical starting point (i.e., the root node) of the information tree. The data packet of a single alarm message is parsed to extract key index fields, including: personnel identifier (e.g., employee ID "W00123"); alarm time (timestamp T accurate to milliseconds). start Initial physiological abnormality type: such as "tachycardia" or "sudden drop in blood pressure". Encapsulate the above fields as the root node of a tree structure. root In terms of data structure, this node is defined as the individual triggering source of the incident's evolution.

[0092] Node root ={ID:"W00123",Time:T start ,Type:"Physio_Alert",Children: } At this point, the node does not yet contain environmental information; it only represents a sudden change in the person's own physiological state.

[0093] Step S53: Based on the association identifier carried in the secondary alarm information, retrieve the secondary alarm record that matches the root node in time and space, and attach the secondary alarm information that represents the environmental coupling risk as a child node to the root node to form a parent-child association link.

[0094] Specifically, after the root node is established, the corresponding environmental risk factors are identified based on the association identifier, and branches of the tree are constructed. Using the association identifier carried in the secondary alarm information (usually containing the same employee ID as the root node and a similar time window), secondary alarm information is retrieved from the database. Secondary alarm information R that meets the following conditions is searched. sec : |Time(R) sec )-Time(Node root )∣<Δt threshold AND Loc(R sec )≈Loc(Node root ) Where Δt threshold The preset time threshold (e.g., 5 minutes) is used, and Loc is the coordinate of the work area.

[0095] The retrieved secondary alarm information characterizing environmental coupling risks (such as "high temperature and humidity" and "excessive toxic gas") is encapsulated into child nodes (Node). child and mount it to Node. root under.

[0096] Step S55: The personalized safety data range used to generate the first alarm information and the environmental operation parameters used to generate the second alarm information are mapped to the attribute fields of the root node and child nodes, respectively.

[0097] Specifically, to enrich the details of the tree, the parameters used to generate alarms are mapped to the specific attributes of the nodes.

[0098] Root node attribute mapping: Maps personalized safety data ranges (such as heart rate zones [60, 100]) and the actual values ​​when an alarm is triggered (such as 135) to Nodes. root The attribute field Attributes_Physio.

[0099] Child node attribute mapping: Map the extracted environmental operation parameters (such as temperature 38℃, humidity 90%) to Nodes. child The attribute field Attributes_Env.

[0100] Through this mapping, each node in the tree is not only a state marker, but also a container containing detailed context data.

[0101] Step S57: Serialize and encapsulate the root node, child nodes, and attribute fields to generate a safety production alarm information tree for visual display of the accident evolution process.

[0102] Specifically, the constructed tree structure is finally serialized to generate a data object that can be directly parsed by the front-end visualization component. The root node, child nodes, and their attribute fields are encapsulated in JSON or XML format. The front-end system parses this JSON data and displays the accident evolution process in the form of a topology diagram or timeline tree: starting from an abnormal heart rate in a person (root node), branches pointing to high temperature and humidity in the environment (child nodes), thus helping safety managers to clearly identify the root cause and evolution logic of the accident at a glance.

[0103] This embodiment constructs a safety production alarm information tree. First, it extracts the personnel identifier, alarm time, and initial physiological abnormality type from primary alarm information and encapsulates them as a root node, thus establishing the individual triggering source of the alarm event. Next, based on the association identifiers carried in secondary alarm information, it retrieves secondary alarm records that match the root node in time and space. Secondary alarm information representing environmental coupling risks is then attached as child nodes to the root node, forming a parent-child association link. Simultaneously, the personalized safety data range used to generate primary alarm information and the environmental operation parameters used to generate secondary alarm information are mapped to the attribute fields of the root node and child nodes, respectively, to enrich the information context. Finally, the root node, child nodes, and their attribute fields are serialized and encapsulated to generate a visualized safety production alarm information tree, clearly displaying the evolution of the accident. This series of steps not only improves the traceability and analyzability of accident information but also enhances the efficiency of safety management and decision support capabilities.

[0104] Accordingly, please refer to Figure 7 A block diagram of a shipbuilding process production data analysis and alarm device provided in this application embodiment, the device comprising: The primary alarm unit 101 is used to perform preliminary analysis on the production data collected during the shipbuilding process according to the preset primary safety production rules, generate primary alarm information, and send the primary alarm information to the alarm equipment and safety officer at the production station. The secondary alarm unit 103 is used to perform secondary intelligent analysis based on preset secondary safety production rules, combined with production data and primary alarm information. Under the condition that the analysis results meet the preset conditions, it generates secondary alarm information and sends the secondary alarm information to the alarm equipment and safety officer. The information tree generation unit 105 is used to generate a safety production alarm information tree based on primary alarm information and secondary alarm information, so as to visualize the evolution process of the accident.

[0105] In some alternative implementations, production data includes personnel data, equipment data, and environmental data; wherein, Personnel data includes employee ID, name, weight, height, heart rate, blood pressure, blood oxygen saturation, limb behavior, spatial positioning, horizontal movement speed, and vertical movement speed; Equipment data includes process station, equipment name, equipment operating parameters, production plan, production object, and quantity of finished products; Environmental data includes production area, process station, temperature, humidity, wind speed, metal dust, welding fumes, noise, paint mist, and harmful gases.

[0106] In some optional implementations, the primary alarm unit 101 includes: Extract personnel dynamic data from production data; Based on the personnel safety rules in the safety production rules, the dynamic data of personnel is analyzed to generate corresponding alarm information.

[0107] In some optional implementations, the primary alarm unit 101 includes: Obtain the static characteristic parameters of the personnel, and generate the initial blood pressure status curve and initial heart rate status curve for the personnel based on the preset physiological characteristic model; Based on the initial blood pressure and initial heart rate curves, the range of personalized safety data for the fit personnel is defined. Compare the personnel dynamic data in the production data with the corresponding personalized safety data range; An alarm will be generated if the personnel dynamic data exceeds the range of personalized security data.

[0108] In some alternative implementations, the secondary alarm unit 103 includes: In response to an alarm message, the system obtains the personalized safety data range and current personnel dynamic data on which the alarm message was generated, and extracts environmental operation parameters that are spatially and temporally related to personnel dynamic data from the production data. The system then integrates the personalized safety data range, personnel dynamic data, and environmental operation parameters to construct a secondary analysis feature vector set. Based on the feature vector set of secondary analysis, the correlation between the extent to which the dynamic data of personnel exceeds the range of personalized safety data and the environmental operation parameters is determined by secondary safety production rules, and a comprehensive safety risk value is generated. The comprehensive safety risk value is compared with the preset intervention threshold. If the comprehensive safety risk value exceeds the intervention threshold, a secondary alarm message is generated, which includes the risk level, recommended handling measures, and related environmental parameters.

[0109] In some alternative implementations, the secondary alarm unit 103 includes: Based on the feature vector set of the second-order analysis, the deviation of the dynamic data of personnel from the baseline in the range of personalized safety data is calculated, and the deviation is mapped to the preset physiological risk level. Environmental operation parameters are extracted from the feature vector set of the secondary analysis, and independent risk assessments are performed on the environmental operation parameters according to the preset environmental safety rules to generate the corresponding environmental risk level. The coupling rule set in the secondary safety production rules is invoked to associate and match the physiological risk level with the environmental risk level to determine the risk amplification factor; Based on the risk amplification coefficient and combined with the initial weights of physiological risk level and environmental risk level, the final comprehensive safety risk value is generated through weighted calculation.

[0110] In some optional implementations, the information tree generation unit 105 includes: Starting with a single alarm message, the personnel identifier, alarm time, and initial physiological abnormality type are extracted from the alarm message and encapsulated as the root node of the safety production alarm information tree to establish the individual triggering source of the alarm event. Based on the association identifier carried in the secondary alarm information, the secondary alarm record that matches the root node in time and space is retrieved. The secondary alarm information that represents the environmental coupling risk is used as a child node and attached to the root node to form a parent-child association link. The personalized safety data range used to generate the first alarm message and the environmental operation parameters used to generate the second alarm message are mapped to the attribute fields of the root node and child nodes, respectively. The root node, child nodes, and attribute fields are serialized and encapsulated to generate a safety production alarm information tree for visual display of the accident evolution process.

[0111] In some alternative embodiments, the apparatus is also used for: Based on the anomaly type in the primary alarm information and the associated environmental parameters in the secondary alarm information, a pre-prepared emergency response plan is matched. The matched emergency response plan will be sent to the safety officer as a response suggestion.

[0112] In some alternative implementations, the alarm device is an audible and visual alarm installed at the production site, or a smart terminal carried by personnel.

[0113] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0114] In this embodiment, a shipbuilding process production data analysis alarm device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0115] Please see Figure 8 , Figure 8 This application provides a schematic diagram of the structure of a computer device, as shown in the embodiment of the present application. Figure 8 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 8 Take a processor 10 as an example.

[0116] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GPA), or any combination thereof.

[0117] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0118] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0119] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0120] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0121] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded over a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the methods shown in the above embodiments are implemented.

[0122] The apparatus and units described in the above embodiments can be implemented by a computer chip or physical entity, or by a product with a certain function. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0123] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0124] Those skilled in the art will understand that the embodiments of this application can be provided as methods or apparatus. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, and devices according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0126] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0127] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0128] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0129] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the apparatus embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0130] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

[0131] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for analyzing and alarming production data during shipbuilding, characterized in that, The method includes: According to the preset safety production rules, the production data collected during the ship construction process is preliminarily analyzed to generate an alarm message, which is then sent to the alarm equipment and safety officer at the production station. According to the preset secondary safety production rules, a secondary intelligent analysis is performed by combining the production data and the primary alarm information. If the analysis results meet the preset conditions, a secondary alarm information is generated and sent to the alarm device and the safety officer. Based on the primary alarm information and the secondary alarm information, a safety production alarm information tree is generated to visualize the accident evolution process.

2. The method according to claim 1, characterized in that, The production data includes personnel data, equipment data, and environmental data; among which, The personnel data includes employee number, name, weight, height, heart rate, blood pressure, blood oxygen saturation, limb behavior, spatial positioning, horizontal movement speed, and vertical movement speed. The equipment data includes process station, equipment name, equipment operating parameters, production plan, production object, and quantity of finished products; The environmental data includes production area, process station, temperature, humidity, wind speed, metal dust, welding fumes, noise, paint mist, and harmful gases.

3. The method according to claim 1, characterized in that, The process involves preliminary analysis of production data collected during shipbuilding, based on preset safety production rules, to generate an alarm message, including: Extract personnel dynamic data from the production data; Based on the personnel safety rules in the aforementioned safety production rules, the dynamic data of the personnel is analyzed to generate corresponding alarm information.

4. The method according to claim 3, characterized in that, The process involves analyzing the personnel dynamic data based on the personnel safety rules within the aforementioned safety production rules to generate corresponding alarm information, including: The static characteristic parameters of the personnel are obtained, and based on the preset physiological characteristic model, the initial blood pressure state curve and the initial heart rate state curve for the personnel are generated. Based on the initial blood pressure curve and the initial heart rate curve, a range of personalized safety data suitable for the individual is defined. Compare the personnel dynamic data in the production data with the corresponding range of personalized safety data; When the personnel dynamic data exceeds the range of the personalized security data, an alarm message is generated.

5. The method according to claim 1, characterized in that, The step involves performing secondary intelligent analysis based on preset secondary safety production rules, combining the production data and the primary alarm information, and generating secondary alarm information under preset conditions, including: In response to the alarm information, the personalized safety data range and current personnel dynamic data on which the alarm information was generated are obtained, and environmental operation parameters that are spatially and temporally related to the personnel dynamic data are extracted from the production data. The personalized safety data range, the personnel dynamic data and the environmental operation parameters are fused together to construct a secondary analysis feature vector set. Based on the secondary analysis feature vector set, the correlation between the extent to which the personnel dynamic data exceeds the range of the personalized safety data and the environmental operation parameters is determined through the secondary safety production rules, thereby generating a comprehensive safety risk value; The comprehensive safety risk value is compared with a preset intervention threshold. If the comprehensive safety risk value exceeds the intervention threshold, a secondary alarm message containing the risk level, recommended handling measures, and related environmental parameters is generated.

6. The method according to claim 5, characterized in that, The process of determining the correlation between the extent to which the personnel dynamic data exceeds the range of the personalized safety data and the environmental operation parameters based on the secondary analysis feature vector set and the secondary safety production rules, and generating a comprehensive safety risk value, includes: Based on the set of secondary analysis feature vectors, the deviation of the personnel dynamic data from the baseline in the range of personalized safety data is calculated, and the deviation is mapped to a preset physiological risk level. The environmental operation parameters are extracted from the set of secondary analysis feature vectors, and an independent risk assessment is performed on the environmental operation parameters according to the preset environmental safety rules to generate the corresponding environmental risk level. The coupling rule set in the secondary safety production rules is invoked to associate and match the physiological risk level with the environmental risk level to determine the risk amplification coefficient; Based on the risk amplification coefficient and combined with the initial weights of the physiological risk level and the environmental risk level, a final comprehensive safety risk value is generated through weighted calculation.

7. The method according to claim 1, characterized in that, The step of generating a safety production alarm information tree based on the primary alarm information and the secondary alarm information to visually display the accident evolution process includes: Using the alarm information as the starting point, the personnel identifier, alarm time, and initial physiological abnormality type in the alarm information are extracted and encapsulated as the root node of the safety production alarm information tree to establish the individual triggering source of the alarm event. Based on the association identifier carried in the secondary alarm information, secondary alarm records that match the root node in time and space are retrieved, and secondary alarm information that represents the risk of environmental coupling is used as a child node and attached to the root node to form a parent-child association link. The personalized safety data range used to generate the first alarm information and the environmental operation parameters used to generate the second alarm information are respectively mapped to the attribute fields of the root node and the child node. The root node, child nodes, and attribute fields are serialized and encapsulated to generate the safety production alarm information tree for visual display of the accident evolution process.

8. The method according to claim 1, characterized in that, The method further includes: Based on the anomaly type in the primary alarm information and the associated environmental parameters in the secondary alarm information, a pre-prepared emergency response plan is matched. The matched emergency response plan will be sent to the safety officer as a response suggestion.

9. The method according to claim 1, characterized in that, The alarm device is either an audible and visual alarm installed at the production site, or a smart terminal carried by personnel.

10. A production data analysis and alarm device for shipbuilding process, characterized in that, The device includes: The primary alarm unit is used to perform preliminary analysis on the production data collected during the shipbuilding process according to the preset primary safety production rules, generate primary alarm information, and send the primary alarm information to the alarm equipment and safety officer at the production workstation. The secondary alarm unit is used to perform secondary intelligent analysis based on preset secondary safety production rules, combined with the production data and the primary alarm information, generate secondary alarm information under the condition that the analysis results meet preset conditions, and send the secondary alarm information to the alarm device and the safety officer. The information tree generation unit is used to generate a safety production alarm information tree based on the primary alarm information and the secondary alarm information, so as to visualize the evolution process of the accident.

Images