Self-adaptive adjustment recording method and system of intelligent safety helmet

Abstract

The invention relates to the technical field of protective equipment, and discloses a self-adaptive adjustment recording method and system for an intelligent safety helmet, and the method comprises the steps: firstly obtaining the physiological and environmental data of the intelligent safety helmet worn by a target operator, determining a physiological stress state, and constructing an operation sensing network; marking dynamic coupling characteristics, calculating an operation safety value, simulating an emergent risk environment and constructing self-adaptive adjustment logic; the logic and the early warning rule are integrated to generate a regulation and control instruction, and feedback parameters are obtained to calculate a tightness regulation index; and finally, adjusting unit parameters according to the indexes, generating operation records, extracting efficiency data, and formulating a self-adaptive adjustment scheme. The wearing comfort of the intelligent safety helmet can be improved, and the operation safety protection capability can be enhanced.

Description

Technical Field

[0001] The invention relates to a self-adaptive adjustment and recording method and system for an intelligent safety helmet, belonging to the technical field of protective equipment. Background Art

[0002] The smart safety helmet is an industrial safety equipment that integrates multiple sensors to monitor the operator's physiological state and environmental parameters in real time, aiming to improve safety and comfort in high-risk work scenarios.

[0003] However, existing implementation methods mostly rely on fixed rules or single-point sensor feedback, such as preset tightness or static warning systems, which use simple threshold warnings or manual adjustment logic and lack adaptive processing of dynamic working conditions. Such methods are difficult to respond to sudden changes in physiological stress states and sudden environmental interference in real time, resulting in adjustment lag and low safety warning accuracy. They also ignore the comprehensive assessment of risk indexes, increasing the incidence of operational accidents. Therefore, an adaptive adjustment and recording method for smart helmets is needed to improve the wearing comfort of smart helmets and enhance operational safety protection capabilities. Summary of the Invention

[0004] The present invention provides a method and system for adaptively adjusting and recording a smart helmet, the main purpose of which is to improve the wearing comfort of the smart helmet and enhance the safety protection capability of work.

[0005] To achieve the above objectives, the present invention provides a method for adaptively adjusting and recording a smart helmet, comprising:

[0006] Acquiring physiological data and environmental data of the smart helmet when worn by a target worker, determining the physiological stress state of the smart helmet under different working conditions based on the physiological data and the environmental data, and constructing a work perception network corresponding to the smart helmet based on the physiological stress state;

[0007] Marking dynamic coupling features corresponding to the posture sensor and the light sensor in the operation perception network, extracting a posture stability coefficient and an environmental interference threshold from the dynamic coupling features, and calculating an operational safety value of the smart helmet under comprehensive operation based on the posture stability coefficient and the environmental interference threshold;

[0008] Based on the operational safety value, simulating the operational risk environment of the smart helmet under an emergency situation, and constructing adaptive adjustment logic corresponding to the smart helmet according to the operational risk environment;

[0009] Integrating the adaptive adjustment logic with preset multi-level warning rules to generate dynamic control instructions corresponding to the smart helmet, obtaining instruction feedback parameters after the dynamic control instructions are executed, and calculating the tightness adjustment index corresponding to the smart helmet based on the instruction feedback parameters;

[0010] Based on the tightness adjustment index, the unit working parameters corresponding to the posture adjustment unit in the smart safety helmet are dynamically adjusted. Based on the unit working parameters, a comprehensive operation record corresponding to the smart safety helmet is generated, and the safety performance data in the comprehensive operation record is extracted. Based on the performance data, an adaptive adjustment plan corresponding to the smart safety helmet is formulated.

[0011] Optionally, constructing a work perception network corresponding to the smart helmet based on the physiological stress state includes:

[0012] Analyzing the state response stage corresponding to the physiological stress state;

[0013] identifying characteristic physiological fluctuation segments in the state response phase;

[0014] Analyzing the operation risk level corresponding to the characteristic physiological fluctuation segment;

[0015] Formulate operation monitoring rules corresponding to the operation risk level;

[0016] Based on the operation monitoring rules, a operation perception network corresponding to the smart safety helmet is constructed.

[0017] Optionally, marking the dynamic coupling features corresponding to the posture sensor and the light sensor in the operation perception network includes:

[0018] Acquire a posture data sequence corresponding to a posture sensor and a light sensing data sequence corresponding to a light sensing sensor in the operation perception network;

[0019] Synchronously aligning the time domain sampling points corresponding to the posture data sequence and the light sensing data sequence;

[0020] Based on the time domain sampling points, constructing a posture-light joint distribution map corresponding to the posture sensor and the light sensor;

[0021] Extracting time-varying fluctuation points in the posture-illumination joint distribution map;

[0022] Based on the time-varying fluctuation points, dynamic coupling features corresponding to the posture sensor and the light sensor in the operation perception network are marked.

[0023] Optionally, the calculating the operational safety value of the smart helmet under comprehensive operation based on the posture stability coefficient and the environmental interference threshold includes:

[0024] analyzing the attitude-sensitive factor corresponding to the attitude stability coefficient;

[0025] obtaining an environmental compensation coefficient and an environmental disturbance real-time value corresponding to the environmental interference threshold;

[0026] combining the attitude-sensitive factor, the environmental compensation coefficient, and the environmental disturbance real-time value, and calculating the operation safety value of the intelligent safety helmet under comprehensive operation by using the following formula:

[0027]

[0028] wherein, the operation safety value of the intelligent safety helmet under comprehensive operation, a safety calibration constant, an attitude-sensitive factor, the attitude stability coefficient, an environmental compensation coefficient, an environmental disturbance real-time value, the environmental interference threshold, a dynamic coupling gain, a risk accumulation amount, a risk lower limit.

[0029] Optionally, the operation safety value is used to simulate the operation risk environment of the intelligent safety helmet under an emergency condition, including:

[0030] analyzing a safety threshold baseline corresponding to the operation safety value;

[0031] determining a typical emergency scenario in which a wearer of the intelligent safety helmet is located based on the safety threshold baseline;

[0032] analyzing a trigger probability vector corresponding to the typical emergency scenario;

[0033] quantifying an instantaneous stress parameter corresponding to the intelligent safety helmet based on the trigger probability vector;

[0034] simulating the operation risk environment of the intelligent safety helmet under an emergency condition based on the instantaneous stress parameter.

[0035] Optionally, the adaptive adjustment logic corresponding to the intelligent safety helmet is constructed according to the operation risk environment, including:

[0036] extracting a key risk element in the operation risk environment;

[0037] setting an adjustment priority corresponding to the intelligent safety helmet based on the key risk element;

[0038] Obtaining a preset adjustment plan that matches the adjustment priority;

[0039] Analyzing the logical triggering conditions in the preset adjustment plan;

[0040] Based on the logic triggering conditions, an adaptive adjustment logic corresponding to the smart helmet is constructed.

[0041] Optionally, the step of integrating the adaptive adjustment logic with preset multi-level warning rules to generate dynamic control instructions corresponding to the smart helmet includes:

[0042] Extracting key condition elements in the adaptive adjustment logic;

[0043] Clarify the warning execution method corresponding to the preset multi-level warning rules;

[0044] Based on the key condition elements and the warning execution mode, constructing a rule decision entry corresponding to the smart helmet;

[0045] Simulate typical warning scenarios corresponding to the rule decision items;

[0046] Based on the typical warning scenario, dynamic control instructions corresponding to the smart helmet are generated.

[0047] Optionally, obtaining an instruction feedback parameter after the dynamic control instruction is executed includes:

[0048] Collecting raw response data from the posture sensor and the light sensor when the dynamic control instruction is executed;

[0049] Performing denoising processing on the original response data to obtain denoised response data;

[0050] extracting a stability indicator from the denoised response data;

[0051] Based on the stability index and the preset environmental interference threshold, the instruction feedback parameters of the dynamic control instruction after execution are analyzed.

[0052] Optionally, dynamically adjusting a unit operating parameter corresponding to a posture adjustment unit in the smart helmet based on the tightness adjustment index includes:

[0053] Analyzing the head pressure level corresponding to the tightness adjustment index;

[0054] Analyzing the adjustment fluctuation period corresponding to the head pressure level;

[0055] Dividing the adjustment fluctuation cycle into loose and tight state stages;

[0056] Counting the unit response parameters in the loose and tight state stages;

[0057] Based on the unit response parameters, the unit working parameters corresponding to the posture adjustment unit are dynamically adjusted.

[0058] In order to solve the above problems, the present invention also provides an adaptive adjustment and recording system for a smart helmet, the system comprising:

[0059] a network construction module for acquiring physiological data and environmental data of the smart helmet when worn by a target worker, determining the physiological stress state of the smart helmet under different working conditions based on the physiological data and the environmental data, and constructing a work perception network corresponding to the smart helmet based on the physiological stress state;

[0060] a safety value calculation module, configured to mark dynamic coupling features corresponding to the posture sensor and the light sensor in the operation perception network, extract a posture stability coefficient and an environmental interference threshold from the dynamic coupling features, and calculate an operational safety value of the smart helmet under comprehensive operation based on the posture stability coefficient and the environmental interference threshold;

[0061] a logic construction module, configured to simulate, based on the operational safety value, an operational risk environment of the smart helmet under an emergency situation, and construct an adaptive adjustment logic corresponding to the smart helmet according to the operational risk environment;

[0062] an index calculation module, configured to integrate the adaptive adjustment logic with preset multi-level warning rules, generate dynamic control instructions corresponding to the smart helmet, obtain instruction feedback parameters after the dynamic control instructions are executed, and calculate the tightness adjustment index corresponding to the smart helmet based on the instruction feedback parameters;

[0063] A plan formulation module is used to dynamically adjust the unit working parameters corresponding to the posture adjustment unit in the smart safety helmet based on the tightness adjustment index, generate a comprehensive operation record corresponding to the smart safety helmet based on the unit working parameters, and extract safety performance data from the comprehensive operation record, and formulate an adaptive adjustment plan corresponding to the smart safety helmet based on the performance data.

[0064] Compared with the problems described in the background technology, the present invention can capture the physical state of the operator and the changes in the surrounding environment in real time by obtaining the physiological data and environmental data of the smart safety helmet when worn by the target operator, providing data support for accurately judging the physiological stress state, realizing comprehensive perception of the working scene, and thus laying a reliable data foundation for subsequent adaptive adjustment and safety assessment. The present invention can break the isolation of single sensor data by marking the dynamic coupling characteristics corresponding to the posture sensor and the light sensor in the working perception network, revealing the correlation between the two in different working scenarios, and improving the comprehensive perception ability of complex working conditions. At the same time, it lays the foundation for the subsequent extraction of key feature parameters, and enhances the adaptability and response accuracy of the smart safety helmet to the dynamic working environment. Furthermore, based on the operational safety value, the present invention simulates the working risk environment of the smart safety helmet in an emergency situation, and can extend the static safety assessment to the dynamic risk deduction, thereby providing The invention can expose potential safety hazards in advance, help improve the resilience of smart helmets to complex dangers, shift from passive protection to active prediction, and strengthen the full process protection of operation safety. Furthermore, the invention integrates the adaptive adjustment logic with the preset multi-level warning rules to generate dynamic control instructions corresponding to the smart helmet, which can organically integrate real-time adjustment needs with the hierarchical warning mechanism. It can strengthen the gradient of safety warnings through multi-level warnings, improve the comprehensive effectiveness of instructions, and make smart helmets form synergy in response timeliness and risk warning intensity, and comprehensively enhance the dynamic management and control capabilities of operation safety. Finally, the invention dynamically adjusts the unit working parameters corresponding to the posture adjustment unit in the smart helmet based on the tightness adjustment index, so that the posture adjustment can accurately adapt to the current tightness of the hat body, avoid posture monitoring and adjustment deviations due to inappropriate tightness, enhance the adaptability of smart helmets to complex operation scenarios, and consolidate the safety protection foundation from the hardware adaptation dimension. Therefore, the adaptive adjustment recording method and system of a smart helmet provided by the embodiment of the invention can improve the wearing comfort of the smart helmet and enhance the safety protection capability of the operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 A schematic flow chart of a method for adaptively adjusting and recording a smart helmet according to an embodiment of the present invention;

[0066] Figure 2 A schematic diagram of the overall logical framework of a method for adaptively adjusting and recording a smart helmet provided in one embodiment of the present invention;

[0067] Figure 3 A schematic diagram of modules for implementing the adaptive adjustment and recording system of a smart helmet provided in one embodiment of the present invention.

[0068] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0069] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0070] The embodiments of the present application provide a method for adaptively adjusting and recording a smart helmet. The method can be performed by at least one of electronic devices, such as a server or a terminal, that can be configured to perform the method provided by the embodiments of the present application. In other words, the method can be performed by software or hardware installed on a terminal or server. The server can include, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0071] Reference Figure 1 FIG. 1 is a flow chart of a method for self-adapting and recording a smart helmet according to an embodiment of the present invention. In this embodiment, the method for self-adapting and recording a smart helmet includes:

[0072] S1. Acquire physiological data and environmental data of a smart helmet when worn by a target operator, determine the physiological stress state of the smart helmet under different operating conditions based on the physiological data and the environmental data, and construct an operation perception network corresponding to the smart helmet based on the physiological stress state.

[0073] By acquiring physiological and environmental data of the target worker wearing the smart helmet, the present invention can capture the worker's physical condition and changes in the surrounding environment in real time, provide data support for accurate judgment of physiological stress status, achieve comprehensive perception of the working scene, and thus lay a reliable data foundation for subsequent adaptive adjustment and safety assessment.

[0074] Among them, the smart safety helmet refers to an intelligent equipment that integrates multiple sensors (such as heart rate sensors, posture sensors, temperature and humidity sensors, etc.) and adjustment units. It can monitor the operator's status and environmental parameters in real time, and automatically adjust the wearing status according to the monitoring results. For example, when the operator's heart rate is detected to exceed 120 beats / minute and the ambient temperature reaches 35°C, the ventilation module can be automatically turned on; the target operator refers to a person who needs to wear a smart safety helmet to perform specific operations. They are in various high-risk operation scenarios, and their physiological state and operating behavior directly affect the safety of the operation. For example, workers performing high-altitude operations on construction sites need their head posture stability and physiological stress response to be monitored in real time to ensure work safety; the physiological data refers to various parameters reflecting the operator's physical state collected by the physiological sensors carried by the smart safety helmet, including heart rate, body temperature, respiratory rate, skin conductivity, etc. For example, when the operator When performing high-intensity work, the sensor may detect that the worker's heart rate rises to 130 beats / minute and the body temperature reaches 37.8°C. These data can reflect the worker's physiological load. The environmental data refers to various parameters of the working environment obtained by the smart helmet through environmental sensors, including temperature, humidity, light intensity, noise decibels, and harmful gas concentrations. For example, when working in a chemical workshop, the environment temperature may be detected as 28°C, humidity as 65%, and harmful gas concentration as 0.02%. These data provide a basis for assessing the impact of the environment on the worker. Optionally, the physiological data obtained when the target worker wears the smart helmet can be achieved through bioelectric signal acquisition technology, such as using a PPG photoplethysmography sensor to monitor heart rate variability in real time to obtain physiological data. The environmental data obtained when the target worker wears the smart helmet can be achieved through multi-parameter environmental sensing technology, such as using the Bosch BME680 integrated environmental sensor to detect temperature, humidity, and atmospheric pressure to obtain environmental data.

[0075] Furthermore, the present invention determines the physiological stress state of the smart safety helmet under different working conditions based on the physiological data and the environmental data, can accurately correlate the operator's physical reaction with the environmental impact, ensure the real-time capture of the operator's stress changes, and at the same time provide a targeted state benchmark for the adaptive adjustment of the smart safety helmet, thereby improving the accuracy and timeliness of the adjustment, and thereby enhancing the initiative of work safety protection.

[0076] Among them, the physiological stress state refers to the physical stress response state of the operator caused by environmental stimulation or changes in physiological load under different working conditions. It is obtained through comprehensive analysis of physiological data and environmental data, and can reflect the operator's body's adaptability to the current working environment and potential risks. For example, when the working environment temperature suddenly rises to 38°C, and the operator's heart rate rises from 70 beats / minute in a resting state to 140 beats / minute and the breathing rate reaches 25 times / minute, it can be determined that the operator is in a moderate physiological stress state, indicating that the body has an obvious stress response and requires timely intervention. Optionally, the determination of the physiological stress state of the smart safety helmet under different working conditions can be achieved through a machine learning classification algorithm, such as: using a support vector machine (SVM) model to analyze heart rate variability and skin electrical response data to obtain the physiological stress state.

[0077] Furthermore, based on the physiological stress state, the present invention constructs an operation perception network corresponding to the smart safety helmet, which can integrate scattered physiological and environmental data to form a multi-dimensional, interconnected perception system, and can capture the dynamic correlation between the operator's status and environmental changes in real time, providing a structured framework to ensure comprehensive perception of complex work scenarios and enhance the overall control ability of the smart safety helmet over work safety.

[0078] Among them, the work perception network refers to a collaborative perception system built based on physiological stress status and composed of multiple sensors and data processing nodes. It can integrate physiological data, environmental data and status analysis results in real time to achieve all-round and dynamic perception of the work scene. For example, the network can link the real-time data of heart rate sensors and temperature and humidity sensors with the physiological stress status analysis results to quickly identify the state changes of operators in complex environments and provide data support for subsequent adjustments.

[0079] As an embodiment of the present invention, the operation perception network corresponding to the smart safety helmet is constructed based on the physiological stress state, including: parsing the state response stage corresponding to the physiological stress state; identifying the characteristic physiological fluctuation segment in the state response stage; analyzing the operation risk level corresponding to the characteristic physiological fluctuation segment; formulating operation monitoring rules corresponding to the operation risk level; and constructing the operation perception network corresponding to the smart safety helmet based on the operation monitoring rules.

[0080] Among them, the state response stage refers to the continuous process from abnormal changes in physiological indicators to gradual adaptation of the body or increased stress under different working conditions. It is divided through dynamic analysis of the physiological stress state to reflect the staged response characteristics of the body to environmental stimuli. For example, when working in a high-temperature environment, it can be divided into the initial stress stage (slight fluctuations in physiological indicators), the stress development stage (obvious abnormalities in indicators), the stress stabilization stage (continuous abnormalities in indicators) and the stress relief stage (gradual recovery of indicators). Each stage corresponds to a different body regulation state; the characteristic physiological fluctuation segment refers to a specific period in the state response stage when physiological indicators show significant and representative changes. These fluctuations are closely related to working conditions and environmental changes, and can reflect the key characteristics of the physiological stress state. For example, when an operator switches from working on the ground to working at high altitude, the heart rate may increase from 85 beats / minute to 110 beats / minute and the respiratory rate may increase from 18 beats / minute to 24 beats / minute during the stress development stage. characteristic physiological fluctuation segment, lasting about 3 minutes; the operation risk level refers to a graded assessment of possible safety risks in the operation process based on the severity of the characteristic physiological fluctuation segment and the corresponding operating environment conditions, which is used to quantify the level of operation risk. For example, when an operator has a characteristic physiological fluctuation of a heart rate of more than 130 beats / minute and a body temperature of 38.5°C for 10 minutes in a high temperature environment, and the ambient humidity reaches 75%, it can be determined as a high operation risk level, indicating the existence of safety hazards such as heatstroke; the operation monitoring rules refer to specific specifications formulated according to different operation risk levels to guide smart safety helmets to perform status monitoring and response, including monitoring frequency, data collection scope, warning triggering conditions, etc., to ensure targeted monitoring of operation scenarios with different risk levels. For example, for high-risk levels, the rules may require the collection of physiological and environmental data every 5 seconds. When the heart rate exceeds 140 beats / minute, a level 1 warning is immediately triggered, and relevant data is recorded simultaneously.

[0081] Furthermore, the analysis of the state response stage corresponding to the physiological stress state can be achieved through a time series clustering algorithm, such as: using the K-means clustering method to divide the heart rate variability data into stages, thereby obtaining the state response stage; the identification of the characteristic physiological fluctuation segment in the state response stage can be achieved through a peak detection algorithm, such as: using the Pan-Tompkins algorithm to extract the abnormal fluctuation interval in the ECG signal, thereby obtaining the characteristic physiological fluctuation segment; the analysis of the operation risk level corresponding to the characteristic physiological fluctuation segment can be achieved through a fuzzy logic evaluation model, such as: constructing a fuzzy inference system based on the deviation of physiological parameters, thereby obtaining the operation risk level; the formulation of the operation monitoring rules corresponding to the operation risk level can be achieved through rule engine technology, such as: using the Drools rule engine to configure the risk threshold trigger strategy, thereby obtaining the operation monitoring rules; the construction of the operation perception network corresponding to the smart safety helmet can be achieved through an edge computing architecture, such as: deploying a distributed sensor node network based on the LoRaWAN protocol, thereby obtaining a operation perception network.

[0082] S2. Mark the dynamic coupling features corresponding to the posture sensor and the light sensor in the operation perception network, extract the posture stability coefficient and the environmental interference threshold in the dynamic coupling features, and calculate the operational safety value of the smart safety helmet under comprehensive operation based on the posture stability coefficient and the environmental interference threshold.

[0083] By marking the dynamic coupling characteristics corresponding to the posture sensor and the light sensor in the operation perception network, the present invention can break the isolation of single sensor data, reveal the correlation rules between the two in different operation scenarios, and improve the comprehensive perception ability of complex operation conditions. At the same time, it lays the foundation for the subsequent extraction of key feature parameters and enhances the adaptability and response accuracy of smart safety helmets to dynamic operation environments.

[0084] Among them, the posture sensor refers to a sensor integrated in the smart safety helmet, which is used to monitor the wearing posture of the safety helmet and the movement status of the operator's head in real time. It can collect parameters such as tilt angle, shaking frequency, acceleration, etc. to reflect the stability and movement characteristics of the operator's head posture. For example, when working at high altitude, the sensor can capture the posture data of the operator's head with a forward tilt angle of more than 30° and shaking 2 times per second, providing a basis for judging whether the operator is at risk of imbalance or fatigue; the light sensor refers to a sensor installed on the outside of the smart safety helmet, which is used to detect optical parameters such as light intensity and light change frequency in the working environment. It can convert light signals into electrical signal output to reflect the impact of ambient light on the operator's vision. For example, when working outdoors, the sensor can monitor light changes from a midday light intensity of 8000 lux to 500 lux within 10 seconds after entering a tunnel, providing support for adjusting the sunshade components of a helmet or warning of strong light or weak light interference. The dynamic coupling feature refers to the interrelated and coordinated changes in the data of the posture sensor and the light sensor over time. By analyzing and extracting time-varying fluctuation points, it reflects the dynamic influence relationship between ambient light changes and head posture adjustments. For example, when the light intensity exceeds 5000 lux, the posture tilt angle increases and the fluctuation frequency increases. This "strong light increase-posture tilt intensification" correlation is a typical dynamic coupling feature.

[0085] As an embodiment of the present invention, the marking of the dynamic coupling characteristics corresponding to the posture sensor and the light sensor in the operation perception network includes: obtaining the posture data sequence corresponding to the posture sensor and the light sensor corresponding to the light sensor in the operation perception network; synchronously aligning the time domain sampling points corresponding to the posture data sequence and the light sensor data sequence; based on the time domain sampling points, constructing a posture-lighting joint distribution map corresponding to the posture sensor and the light sensor; extracting time-varying fluctuation points in the posture-lighting joint distribution map; based on the time-varying fluctuation points, marking the dynamic coupling characteristics corresponding to the posture sensor and the light sensor in the operation perception network.

[0086] Among them, the posture data sequence refers to a series of data sets collected by the posture sensor in a continuous time, reflecting the changes in the operator's head posture, including parameters that change with time, such as tilt angle, shaking frequency, acceleration, etc. For example, during a 10-minute operation, data is collected every 0.5 seconds to form a sequence of 200 data points, in which the tilt angle may continuously change from 5° to 25° and then to 8°, fully recording the dynamic process of the posture; the light sensor data sequence refers to the data obtained by the light sensor during the continuous monitoring period, reflecting the changes in ambient light. A series of data sets, consisting of parameters such as light intensity and light change rate over time. For example, in a 15-minute outdoor operation, data is collected every 1 second to form a sequence of 900 data points, which may include a continuous fluctuation record of light intensity rising from 3000 lux to 6000 lux (strong light period) and then falling to 1000 lux (cloud cover); the time domain sampling point refers to the specific time point on the time axis at which the posture data and light perception data are synchronously collected. Each point corresponds to a set of posture parameters and light parameters at the same time, ensuring that the two types of data are synchronized in time. Dimensional matching, for example, sampling points are set at intervals of 1 second, and at the time domain sampling point of the 5th second, the tilt angle of the attitude sensor of 12° and the light intensity of the light sensor of 4500 lux are synchronously recorded to achieve time alignment of the data; the attitude-light joint distribution diagram refers to a diagram that visualizes the synchronized attitude data sequence and the light sensor data sequence in the same coordinate system, with the horizontal axis being time and the vertical axis corresponding to attitude parameters (such as tilt angle) and light parameters (such as light intensity), respectively, to intuitively show the coordinated change relationship between the two over time. For example, the diagram can clearly show The time-varying fluctuation point refers to the time point in the attitude-light joint distribution diagram where the attitude parameters or light parameters significantly deviate from the normal fluctuation range. These points often reflect the abnormal characteristics of the coordinated changes of the two. For example, when the light intensity jumps from 2000 lux to 7000 lux within 10 seconds, the corresponding attitude tilt angle suddenly increases from 8° to 28°. This time point is the time-varying fluctuation point, reflecting the sudden impact of strong light on the operator's head posture.

[0087] Furthermore, the acquisition of the posture data sequence corresponding to the posture sensor in the operation perception network can be achieved through inertial measurement unit acquisition technology, such as: using the MPU6050 six-axis sensor to record three-axis acceleration and angular velocity data, thereby obtaining a posture data sequence; the acquisition of the light data sequence corresponding to the light sensor in the operation perception network can be achieved through spectral analysis technology, such as: using the BH1750 digital light sensor to collect ambient light intensity change data, thereby obtaining a light data sequence; the synchronous alignment of the posture data sequence and the time domain sampling points corresponding to the light data sequence can be achieved through a timestamp matching algorithm, such as: multi-source sensor data synchronization based on the PTP precise time protocol, thereby obtaining time domain sampling points; the construction of the posture-light joint distribution map corresponding to the posture sensor and the light sensor can be achieved through multidimensional data visualization technology, such as: using the Matplotlib library to draw a three-dimensional scatter plot to present the correlation distribution of posture angle and light intensity, thereby obtaining a posture-light joint distribution map; the extraction of time-varying fluctuation points in the posture-light joint distribution map can be achieved through an anomaly detection algorithm, such as: applying Isolation The Forest algorithm identifies outlier data points in the distribution map, thereby obtaining time-varying fluctuation points; the dynamic coupling features corresponding to the posture sensor and the light sensor in the operation perception network can be marked by mutual information calculation technology, such as: quantifying the statistical correlation between posture changes and light fluctuations through KL divergence, thereby obtaining dynamic coupling features.

[0088] By extracting the posture stability coefficient and environmental interference threshold from the dynamic coupling characteristics, the present invention can convert the abstract coupling relationship into quantifiable key parameters, provide an accurate numerical basis for evaluating the operating status, improve the efficiency of judging the operating stability and the degree of environmental interference, and thus optimize the dynamic adjustment logic of the smart helmet.

[0089] Among them, the posture stability coefficient refers to an indicator used to quantify the stability of the operator's head posture, which is calculated by analyzing the fluctuation degree of parameters such as tilt angle and shaking frequency in the posture data sequence. The value range is usually 0-1. The closer to 1, the more stable the posture. For example, during stable operation, if the maximum fluctuation of the tilt angle within 1 minute does not exceed 5° and the shaking frequency is stable at 0.5 times / second, the posture stability coefficient can be 0.85; and before the imbalance of high-altitude operation, the angle fluctuation reaches 15° and the frequency rises to 2 times / second, the coefficient can be reduced to 0.3, which intuitively reflects the change in the posture stability state; the environmental interference threshold refers to the critical value of the environmental factors that significantly interfere with the safety of the operation. It is determined based on the light sensing data sequence and dynamic coupling characteristics. If it exceeds this value Environmental factors can affect the operator's state or operation accuracy. For example, combined with the coupling relationship between light and posture, when the light intensity suddenly rises to more than 6000 lux, the operator's posture stability coefficient drops by more than 30%, and 6000 lux is set as the light-related environmental interference threshold, indicating that the strong light has significantly interfered with the operation stability at this time. Optionally, the extraction of the posture stability coefficient in the dynamic coupling feature can be achieved through variance analysis, such as: using a sliding window to calculate the standard deviation of the three-axis acceleration data to obtain the posture stability coefficient; the extraction of the environmental interference threshold in the dynamic coupling feature can be achieved through percentile statistics, such as: calculating the 95% percentile as the critical value based on the historical light perception data distribution to obtain the environmental interference threshold.

[0090] Furthermore, the present invention calculates the operational safety value of the smart safety helmet under comprehensive operations based on the posture stability coefficient and the environmental interference threshold, and can integrate the two key parameters into a unified safety assessment index, thereby improving the comprehensiveness and accuracy of the safety assessment. At the same time, it provides a core reference for subsequent simulation of risk environments and construction of adjustment logic, thereby enhancing the safety control capabilities of smart safety helmets in complex operation scenarios.

[0091] Among them, the operational safety value refers to a quantitative indicator that comprehensively evaluates the overall safety status of the smart safety helmet during operation. It is calculated by integrating parameters such as the posture stability coefficient and the environmental interference threshold. The value range is usually 0-100. The higher the value, the higher the operation safety. For example, when the posture stability coefficient is 0.8 and the environment does not exceed the interference threshold, the operational safety value can be set to 85; if the coefficient drops to 0.4 and the environment exceeds the standard, the value can be reduced to 40, which intuitively reflects the comprehensive safety level.

[0092] As an embodiment of the present invention, the calculating of the operational safety value of the smart helmet under comprehensive operation based on the posture stability coefficient and the environmental interference threshold includes:

[0093] Analyzing the attitude sensitivity factor corresponding to the attitude stability coefficient;

[0094] Obtaining an environmental compensation coefficient and a real-time value of environmental disturbance corresponding to the environmental interference threshold;

[0095] The operational safety value of the smart helmet under comprehensive operation is calculated by combining the posture sensitivity factor, the environmental compensation coefficient and the real-time value of the environmental disturbance.

[0096] Among them, the posture sensitivity factor refers to a weight parameter that measures the degree of influence of the posture stability coefficient on the operational safety value, with a value range of 0-1. The higher the value, the greater the influence of posture stability on safety. For example, in high-altitude operation scenarios, the posture sensitivity factor can be set to 0.6, which means that the posture stability coefficient accounts for a higher proportion in the safety assessment; while in static operations, the factor can be reduced to 0.3; the environmental compensation coefficient refers to a correction coefficient used to adjust the weight of the influence of environmental parameters on the operational safety value, with a value of 0-1, and together with the posture sensitivity factor, constitutes an evaluation weight system. For example, in a strong light environment, the environmental compensation coefficient can be set to 0.5 to enhance the influence of the environmental interference threshold on the safety value; in a mild environment, the coefficient can be set to 0.2 to weaken the proportion of environmental factors; the real-time value of environmental disturbance refers to the current value of the environmental parameter collected in real time by the sensor, and the dimension varies with the parameter type (such as temperature in °C, light intensity in °C, etc.). is lux), which directly reflects the degree of interference of the current environment on the operation. For example, when operating in a chemical workshop, the real-time value of the environmental disturbance may be 0.03% of the harmful gas concentration and 36°C of the temperature. These values ​​are used to compare with the environmental disturbance threshold. Optionally, the analysis of the posture sensitivity factor corresponding to the posture stability coefficient can be implemented by a multiple regression analysis method, such as: using SPSS software to establish an influencing factor regression model to obtain the posture sensitivity factor; the acquisition of the environmental compensation coefficient corresponding to the environmental interference threshold can be implemented by a Kalman filtering algorithm, such as: using MATLAB's kalman function to perform noise filtering processing to obtain the environmental compensation coefficient; the acquisition of the real-time value of the environmental disturbance corresponding to the environmental disturbance threshold can be implemented by sensor fusion technology, such as: collecting environmental data through an MPU9250 multi-axis sensor to obtain the real-time value of the environmental disturbance.

[0097] As another embodiment of the present invention, the operational safety value of the smart helmet under comprehensive operation is calculated as follows: the operational safety value of the smart helmet under comprehensive operation is calculated using the following formula:

[0098]

[0099] in, Indicates the operational safety value of the smart helmet under comprehensive operation, represents the safety calibration constant, represents the posture sensitivity factor, represents the attitude stability coefficient, represents the environmental compensation coefficient, Indicates the real-time value of environmental disturbance, represents the environmental interference threshold, represents the dynamic coupling gain, represents the cumulative risk, Indicates the lower limit of risk.

[0100] In detail, the safety calibration constant refers to the benchmark value used to unify the dimension of the formula and correct the calculation deviation. It is determined based on historical safety data and equipment characteristics and is a dimensionless constant to ensure that the output of the operational safety value is within a preset reasonable range; the posture stability coefficient refers to an indicator that quantifies the stability of the operator's head posture. It is calculated by analyzing the fluctuation degree of parameters such as the tilt angle and shaking frequency in the posture data sequence. The range is 0-1. The closer to 1, the more stable the posture. For example, during stable operation, the angle fluctuation does not exceed 5° within 1 minute, and the coefficient can be set to 0.85; if the fluctuation reaches 15° before imbalance, the coefficient can be reduced to 0.3, reflecting the stable state of the posture; the environmental interference threshold refers to the critical value for classifying environmental factors that significantly interfere with operational safety. The dimension is consistent with the real-time value of the environmental disturbance and is determined based on the light sensing data and coupling characteristics. If this value is exceeded, the environment affects the stability of the operation. For example, combined with the coupling relationship between light and posture, when the light intensity suddenly rises to more than 6000 lux, the posture stability coefficient drops by 30%, and 6000 lux is the light-type environment. The dynamic coupling gain is a coefficient that quantifies the interaction strength between posture and environmental parameters and is used to correct the impact of the coupling relationship between the two on the safety value. A larger value indicates a more significant coupling effect. For example, in the "strong light-lowering" coupling scenario, the dynamic coupling gain can be set to 1.5 to amplify the combined effects of environmental violations and posture instability, making the safety value more sensitive to risk. The cumulative risk is the cumulative sum of operational risk factors per unit time. It is calculated by continuously monitoring the duration and magnitude of the operational safety value below the critical value, reflecting the cumulative effect of risk. For example, if the operational safety value is below 50 for 5 consecutive minutes and is 10 points lower on average, the cumulative risk can be calculated as 50, indicating that the risk is continuously accumulating. The lower risk limit is a dimensionless critical value that defines the acceptable range of the cumulative risk. A value below this value indicates that the cumulative risk is at a safe level, while a value above this value triggers an alert. For example, the lower risk limit is set to 80 based on the operation type. When the cumulative risk reaches 90, the system determines that the cumulative risk is too high and initiates the enhanced alert mechanism.

[0101] Furthermore, it should be noted that the core purpose of each operation (multiplication, division, addition, exponentiation) in the above formula is to convert nonlinear factors such as posture stability, environmental interference, and risk accumulation into quantifiable safety values ​​through mathematical mapping, while ensuring that the impact of each factor conforms to the physical laws of the actual operation scenario (such as the nonlinear threat of posture instability, the marginal diminishing effect of environmental interference, etc.), and ultimately achieve an accurate assessment of the comprehensive operational safety of the smart helmet.

[0102] S3. Based on the operational safety value, simulate the operational risk environment of the smart helmet under an emergency situation, and construct an adaptive adjustment logic corresponding to the smart helmet according to the operational risk environment.

[0103] Based on the operational safety value, the present invention simulates the operational risk environment of the smart safety helmet under emergency situations, and can extend static safety assessment to dynamic risk deduction, expose potential safety hazards in advance, help improve the resilience of the smart safety helmet to complex dangers, shift from passive protection to active prediction, and strengthen the full-process protection of operational safety.

[0104] Among them, the emergency situation refers to an abnormal event that occurs suddenly during the operation and may have a significant impact on the safety of the operator or the stability of the operation. It is characterized by sudden occurrence and severe impact, and needs to be identified in combination with the sudden change of the operation safety value. For example, when working outdoors at high altitude, if the wind speed suddenly increases from 3m / s to 12m / s within 10 seconds, and the operator's posture stability coefficient drops from 0.8 to 0.2, and the operation safety value falls below 30, it is determined to be a sudden strong wind interference situation, and an emergency response is required to avoid accidents; the operation risk environment refers to a virtual dangerous operation scene constructed by comprehensively combining the operation safety value, typical emergency scenarios, trigger probability vectors and instantaneous pressure parameters to simulate emergency situations, including environmental interference, posture risk and other multi-factor interactions, which is used to test the response capability of safety helmets, simulate the dangerous environment of "strong light + strong wind" superposition and a sudden drop in operation safety value, and evaluate the protective effectiveness of safety helmets.

[0105] As an embodiment of the present invention, simulating the operating risk environment of the smart safety helmet under an emergency situation based on the operational safety value includes: parsing the safety threshold baseline corresponding to the operational safety value; determining the typical emergency scenario in which the wearer of the smart safety helmet is located based on the safety threshold baseline; analyzing the trigger probability vector corresponding to the typical emergency scenario; quantifying the instantaneous pressure parameter corresponding to the smart safety helmet based on the trigger probability vector; and simulating the operating risk environment of the smart safety helmet under an emergency situation based on the instantaneous pressure parameter.

[0106] Among them, the safety threshold baseline refers to the benchmark range for the operation safety value based on historical safety operation data, industry standards and the protective performance of smart safety helmets, which is used to distinguish between safe and risky states. For example, after a lot of tests and analysis, the operation safety value is set to 60-90 as a safe interval. If it is lower than 60, it will enter a risk warning state, and if it is higher than 90, it will enter an ultra-safety redundant state. For routine operations, the safety threshold baseline can be set to [50,100] to assist in judging the safety boundary of the operation; the typical emergency scenario refers to an emergency dangerous scenario with common characteristics summarized based on the breakthrough of the safety threshold baseline, combined with factors such as the working environment and posture. For example, when the operation safety value falls below the baseline due to the light intensity jumping from 200 lux to 1000 lux within 10 seconds and the posture stability coefficient dropping from 0.8 to 0.3, it corresponds to "strong light interference causing posture The typical emergency scenario of "posture imbalance caused by strong light interference" can accurately locate the type of danger; the trigger probability vector refers to the quantitative representation of the possibility of triggering each risk factor in the typical emergency scenario, presenting the probability of occurrence of different factors in the form of a vector. For example, in the scenario of "posture imbalance caused by strong light interference", the probability of triggering by strong light mutation is 0.6 and the probability of triggering by posture loss is 0.7, forming a trigger probability vector [0.6, 0.7], which is used to measure the possibility of the outbreak of risk factors in the scenario; the instantaneous pressure parameter refers to a quantitative indicator of the instantaneous risk pressure borne by the smart helmet and the wearer in an emergency situation based on the trigger probability vector and combined with parameters such as the environment and posture in the scenario. For example, the strong light mutation pressure value is 8 and the posture loss pressure value is 7. After calculation by the formula (such as pressure = probability × influence coefficient), the instantaneous pressure parameter 12 is obtained, which reflects the impact intensity of the emergency.

[0107] Furthermore, the analysis of the safety threshold baseline corresponding to the operational safety value can be achieved through a statistical process control method, such as: using an X-bar control chart to calculate the upper and lower limits of historical safety data, thereby obtaining a safety threshold baseline; the determination of the typical emergency scenario in which the operator wearing the smart safety helmet is located can be achieved through a scenario clustering algorithm, such as: using DBSCAN density clustering to classify the accident report text into scenarios, thereby obtaining a typical emergency scenario; the analysis of the trigger probability vector corresponding to the typical emergency scenario can be achieved through a Bayesian network model, such as: constructing a conditional probability table based on prior probability to calculate the possibility of scenario occurrence, thereby obtaining a trigger probability vector; the quantification of the instantaneous pressure parameter corresponding to the smart safety helmet can be achieved through strain gauge sensing technology, such as: using the HX711 pressure sensor module to collect the force data of the hat body, thereby obtaining the instantaneous pressure parameter; the simulation of the operating risk environment of the smart safety helmet under emergency conditions can be achieved through digital twin technology, such as: using the Unity3D engine to build a virtual reality environment for stress testing, thereby obtaining an operating risk environment.

[0108] Based on the operational risk environment, the present invention constructs the adaptive adjustment logic corresponding to the smart safety helmet, which allows the smart safety helmet to dynamically adjust the protection strategy according to the operational risk environment, and can optimize functions such as posture monitoring and environmental response in real time, improve the accuracy of responding to complex dangers, and shift from passive protection to active adaptation, thereby enhancing the timeliness and effectiveness of safety protection during the operation process and building a dynamic safety line of defense for the operator.

[0109] Among them, the adaptive adjustment logic refers to an intelligent decision-making rule built based on logical trigger conditions, which can dynamically adjust the adjustment strategy according to the operational risk environment. It can achieve accurate response in different risk scenarios. For example, in the "strong light + imbalance" scenario, this logic can first trigger the sun visor adjustment (responding to light risk), then start the tightening of the chin strap (responding to posture risk), and adjust the adjustment amplitude according to real-time data, reflecting the dynamic adaptation characteristics.

[0110] As an embodiment of the present invention, constructing the adaptive adjustment logic corresponding to the smart safety helmet according to the operational risk environment includes: extracting key risk factors in the operational risk environment; setting the adjustment priority corresponding to the smart safety helmet based on the key risk factors; obtaining a preset adjustment plan that matches the adjustment priority; parsing the logical trigger conditions in the preset adjustment plan; and constructing the adaptive adjustment logic corresponding to the smart safety helmet based on the logical trigger conditions.

[0111] Among them, the key risk factors refer to the core risk factors extracted from the operating risk environment that have a decisive impact on the safety of the operator or the stability of the operation. They can be determined by analyzing the environmental parameters, posture data and changes in safety values. For example, in the "high temperature + high altitude imbalance" risk environment, the two factors of ambient temperature 38°C and posture stability coefficient 0.3 have the greatest impact on safety, which are the key risk factors and are the core basis for formulating adjustment strategies; the adjustment priority refers to the ranking of the various adjustment functions of the smart safety helmet according to the degree of danger and impact range of the key risk factors. The adjustment functions with high priority will be responded to first. For example, in the "harmful gas leakage + excessive light" scenario, the concentration of harmful gases exceeds the standard and may endanger life. The corresponding ventilation adjustment priority is set to level 1, and the light adjustment is set to level 2 to ensure that high-risk issues are given priority. Processing; The preset adjustment plan refers to a standardized adjustment plan that is pre-formulated for different work risk environments and matches the adjustment priority, including specific adjustment measures, execution steps and parameter ranges. For example, for the risk of "high-altitude posture imbalance", the preset adjustment plan may stipulate: when the posture stability coefficient is lower than 0.4, the chin strap will be automatically tightened (tightened by 2cm) + sound and light warning, providing a standardized process for rapid response; the logical trigger condition refers to the critical judgment standard for initiating a specific adjustment action in the preset adjustment plan, which is set based on the quantitative indicators of key risk factors. If the conditions are met, the corresponding adjustment logic will be triggered. For example, in the high-temperature adjustment plan, the logical trigger condition may be "ambient temperature ≥35℃ and operator body temperature ≥37.5℃". When the sensor detects that these two conditions are met at the same time, the ventilation module will be automatically started.

[0112] Furthermore, the extraction of key risk factors in the operational risk environment can be achieved through principal component analysis, such as: using PCA dimensionality reduction technology to identify the main influencing factors in environmental parameters, thereby obtaining key risk factors; the setting of the adjustment priority corresponding to the smart safety helmet can be achieved through the entropy weight method, such as: calculating the objective weight value of each risk factor based on information entropy, thereby obtaining the adjustment priority; the acquisition of the preset adjustment plan that matches the adjustment priority can be achieved through case reasoning technology, such as: using the CBR system to retrieve the historical optimal response plan library, thereby obtaining the preset adjustment plan; the analysis of the logical trigger conditions in the preset adjustment plan can be achieved through a decision tree algorithm, such as: using the C4.5 algorithm to decompose the conditional branches of the plan execution path, thereby obtaining the logical trigger conditions; the construction of the adaptive adjustment logic corresponding to the smart safety helmet can be achieved through a reinforcement learning method, such as: applying the Q-learning algorithm to optimize the safety parameter adjustment strategy, thereby obtaining the adaptive adjustment logic.

[0113] Specifically, to further understand the execution logic and data flow relationship of the smart helmet system, please refer to Figure 2 ,Should Figure 2 As the core architectural blueprint of the smart helmet system, it clearly presents the complete chain from terminal module collaboration to platform interaction: the smart helmet terminal focuses on functional modules such as positioning, audio and video (for example, the positioning module accurately obtains location, and the audio and video module captures working images), and is the fundamental carrier for data generation and interaction. The Wi-Fi / 4G module serves as a connection hub, transmitting terminal data to the server via protocols such as RTP, SIP, and HTTP. (Streaming media, signaling, and application servers are divided into processing audio and video streams, signaling control, and business logic). The smart helmet management platform and configuration app serve as upper-layer applications, enabling remote control and parameter configuration of the terminal. It should be noted that the associations between the various modules in the framework diagram are essentially an abstract distillation of the "terminal-transmission-platform" interaction logic of the smart helmet. In actual scenarios, the complexity of protocol adaptation (such as dynamic switching of protocols in different network environments) and the diversity of module collaboration (resource scheduling when multiple modules are working simultaneously) are far greater than what is presented in the diagram. This architecture simply presents the core logic and provides an intuitive reference for understanding the systematic operation of the smart helmet system.

[0114] S4. Integrate the adaptive adjustment logic with the preset multi-level warning rules to generate a dynamic control instruction corresponding to the smart helmet, obtain the instruction feedback parameters of the dynamic control instruction after execution, and calculate the tightness adjustment index corresponding to the smart helmet based on the instruction feedback parameters.

[0115] The present invention integrates the adaptive adjustment logic with the preset multi-level warning rules to generate dynamic control instructions corresponding to the smart safety helmet, which can organically integrate real-time adjustment needs with the hierarchical warning mechanism. It can strengthen the gradient of safety warnings through multi-level warnings, improve the comprehensive effectiveness of instructions, and enable the smart safety helmet to form synergy in response timeliness and risk warning intensity, thereby comprehensively enhancing the dynamic management and control capabilities of operational safety.

[0116] The pre-set multi-level warning rules refer to warning specifications with gradient response intensity based on the operational risk level. By setting different thresholds and corresponding warning measures, a layered warning and handling of risks is achieved. The rules cover warning levels, trigger conditions, and response methods. The higher the level, the stronger the warning measures. For example, Level 1 warning (low risk): Operational safety value 70-80, only a helmet vibration prompt; Level 2 warning (medium risk): Value 50-70, audible and visual alarms are activated and data is uploaded; Level 3 warning (high risk): Value < 50, high-frequency alarms are triggered and a distress signal is sent to the monitoring center, forming a step-by-step warning system. The dynamic control instructions are control commands generated after verification of typical warning scenarios and can be dynamically adjusted according to real-time operational status. They integrate adaptive adjustment actions and multi-level warning measures to achieve precise response to risks. For example, an instruction may include "Start the ventilation module to 80% power (adjustment) and issue a 60dB audible and visual alarm (Level 2 warning)" and can be updated in real time as environmental parameters change.

[0117] As an embodiment of the present invention, the integration of the adaptive adjustment logic and the preset multi-level warning rules to generate dynamic control instructions corresponding to the smart safety helmet includes: extracting key condition elements in the adaptive adjustment logic; clarifying the warning execution method corresponding to the preset multi-level warning rules; constructing rule decision entries corresponding to the smart safety helmet based on the key condition elements and the warning execution method; simulating typical warning scenarios corresponding to the rule decision entries; and generating dynamic control instructions corresponding to the smart safety helmet based on the typical warning scenarios.

[0118] Among them, the key condition elements refer to the core judgment indicators extracted from the adaptive adjustment logic that determine whether the adjustment action is started or not, including environmental parameter thresholds, physiological state critical values, etc., which are the basis for triggering regulation and early warning. For example, in the high temperature adjustment logic, the two conditions of "ambient temperature ≥ 36°C and operator body temperature ≥ 37.6°C" that are met at the same time are key condition elements, which directly affect the start of subsequent early warnings and adjustments; the early warning execution method refers to the specific warning means and implementation forms corresponding to different warning levels in the preset multi-level early warning rules, including warning type, intensity, transmission path, etc. For example, the first-level early warning uses a built-in vibrator in the safety helmet (frequency 2 times / second); the second-level early warning superimposes an sound and light alarm (volume 80 decibels, light flashing frequency 1 time / second); the third-level early warning additionally triggers a pop-up prompt from the background monitoring center, forming a hierarchical progression The rule decision entry refers to a specific decision rule constructed based on key condition elements and warning execution methods, which clarifies "what kind of adjustment and warning to perform under what conditions". It is a bridge connecting logic and instructions. For example, a decision entry can be expressed as: "When the ambient temperature is ≥38℃ (key condition), start the first-level adjustment (ventilation intensity 50%) + second-level warning (sound and light alarm)", which clearly stipulates the correspondence between conditions and actions; the typical warning scenario refers to a representative warning scenario simulated according to the rule decision entry, which contains specific risk parameters and response requirements, and is used to verify the rationality and effectiveness of the decision entry. For example, simulating the scenario of "ambient temperature 39℃ + heart rate 135 beats / minute" will trigger the third-level adjustment (ventilation 100%) + third-level warning (high-frequency alarm + background notification) to test the adaptability of the rule in this scenario.

[0119] Furthermore, the extraction of key condition elements in the adaptive adjustment logic can be achieved through a decision rule mining algorithm, such as: using the FP-growth algorithm to identify frequently occurring condition combination patterns, thereby obtaining key condition elements; the warning execution method corresponding to the clearly preset multi-level warning rules can be achieved through a state machine modeling method, such as: using a UML state diagram to define the state transition logic of different risk levels, thereby obtaining a warning execution method; the construction of rule decision items corresponding to the smart safety helmet can be achieved through knowledge graph technology, such as: using the Neo4j graph database to construct a condition-action association network, thereby obtaining rule decision items; the simulation of typical warning scenarios corresponding to the rule decision items can be achieved through discrete event simulation technology, such as: using AnyLogic software to establish a multi-scenario warning response model, thereby obtaining a typical warning scenario; the generation of dynamic control instructions corresponding to the smart safety helmet can be achieved through a real-time decision engine, such as: deploying a Drools rule engine to automatically trigger the optimal control strategy, thereby obtaining a dynamic control instruction.

[0120] By obtaining the instruction feedback parameters after the execution of the dynamic control instruction, the present invention can verify the execution effect and adaptability of the instruction in real time, provide a direct basis for evaluating the rationality of the control logic, and improve the iterative efficiency of the dynamic response of the smart helmet. At the same time, it accumulates practical data for the subsequent improvement of early warning rules and adjustment logic, thereby enhancing the accuracy and adaptability of overall safety management and control.

[0121] Among them, the command feedback parameters refer to comprehensive data reflecting the adjustment effect after the dynamic control command is executed, covering stability indicators, physiological data changes, environmental adaptability, etc., which are used to evaluate the effectiveness of the command. For example, after executing the "turn on ventilation" command, the feedback parameters show: the head stability index increased by 40%, the wearer's heart rate dropped from 95 beats / minute to 82 beats / minute, and the temperature difference between the ambient temperature and the temperature inside the hat was reduced to 3°C. These data together constitute the command feedback parameters.

[0122] As an embodiment of the present invention, obtaining the instruction feedback parameter after the dynamic control instruction is executed includes:

[0123] Collecting raw response data from the posture sensor and the light sensor when the dynamic control instruction is executed;

[0124] Performing denoising processing on the original response data to obtain denoised response data;

[0125] extracting a stability indicator from the denoised response data;

[0126] Based on the stability index and the preset environmental interference threshold, the instruction feedback parameters of the dynamic control instruction after execution are analyzed.

[0127] Among them, the posture sensor refers to a sensor integrated in the smart safety helmet for real-time monitoring of the wearer's head movement posture, which usually includes components such as gyroscopes and accelerometers. It can capture dynamic information such as the head's shaking angle, movement trajectory, and tilt degree. For example, during high-altitude operations, if the wearer's head shakes at a high frequency of more than ±15° within 10 seconds, the posture sensor will record this motion data in real time to provide a basis for subsequent stability analysis; the light sensor refers to a sensor installed on the outer surface of the smart safety helmet for detecting the light intensity of the working environment. It can convert light signals into electrical signals and accurately feedback changes in environmental brightness. For example, in open-air welding operations, when the light sensor detects that the light intensity suddenly rises from 500 lux to 10,000 lux, it will quickly transmit this data to provide an environmental basis for determining whether the sun visor needs to be adjusted; the raw response data refers to the unprocessed initial data collected in real time by the posture sensor and the light sensor during the execution of the dynamic control instruction, which contains redundant information such as the sensor's own noise and environmental interference. Information, for example, when executing the "tighten the hatband" command, the posture sensor collects 100 sets of head shaking data within 2 seconds, of which 8 sets are mixed with abnormal values ​​caused by slight vibration of the sensor. These data are the original response data; the denoised response data refers to the effective data after filtering, smoothing, and other processing of the original response data to eliminate noise and interference information, which is closer to the real physical state. For example, after using the Kalman filter algorithm to process the above 100 sets of original data, 8 sets of abnormal values ​​are removed to obtain 92 sets of continuous and stable head shaking data, which are the denoised response data, which can more accurately reflect the changes in head posture after the hatband is tightened; the stability index refers to the parameters extracted from the denoised response data for quantifying the stability of the head posture, including shaking frequency, angular standard deviation, motion acceleration peak, etc. For example, after calculation, the head shaking frequency before the hatband is adjusted is 4 times / second and the angular standard deviation is 8°, which are reduced to 1.5 times / second and 3° respectively after adjustment. These values ​​are stability indicators, which intuitively reflect the improvement effect of adjustment on posture stability.

[0128] Furthermore, the acquisition of raw response data from the attitude sensor and the light sensor when the dynamic control instruction is executed can be achieved through an embedded data acquisition system, such as: using an STM32 microcontroller in conjunction with the I2C protocol to synchronously read the MPU6050 attitude sensor and the BH1750 light sensor data, thereby obtaining the raw response data; the denoising of the raw response data can be achieved through a digital signal filtering algorithm, such as: using the Kalman filter algorithm in the Python SciPy library to smooth the sensor timing signal, thereby obtaining denoised response data; the extraction of the stability index from the denoised response data can be achieved through a time domain feature analysis method, such as: applying MATLAB to calculate the windowed standard deviation and mean offset as dynamic stability quantitative indicators, thereby obtaining a stability index; the analysis of the instruction feedback parameters after the execution of the dynamic control instruction can be achieved through a control performance evaluation model, such as: establishing an error integral index between the PID control response curve and the ideal curve based on Simulink, thereby obtaining the instruction feedback parameter.

[0129] The present invention calculates the tightness adjustment index corresponding to the smart helmet based on the instruction feedback parameters, and can convert abstract feedback data into a quantifiable basis for adjusting the tightness of the helmet body, accurately matching the real-time status of the operator, and improving the pertinence and comfort of the adjustment action. At the same time, it provides specific parameter support for the iteration of dynamic control instructions, and enhances the balance between safety protection and wearing experience of the smart helmet.

[0130] Among them, the tightness adjustment index refers to the core indicator used to quantify the adaptability of the tightness adjustment strategy of the smart helmet, which comprehensively reflects the impact of factors such as target tightness deviation, feedback delay, and environmental interference on the adjustment effect. The higher the value, the more accurate the adjustment. For example, when Sz is 0.85, it means that the adjustment strategy can better adapt to the current working status; if Sz drops to 0.3, the adjustment logic needs to be optimized.

[0131] As an embodiment of the present invention, the calculating of the tightness adjustment index corresponding to the smart helmet based on the instruction feedback parameter includes:

[0132] parsing the adjustment feedback index in the instruction feedback parameter;

[0133] determining a target tightness position and an actual tightness position corresponding to the smart helmet based on the adjustment feedback index;

[0134] analyzing a reference tightness position corresponding to the target tightness position and the actual tightness position;

[0135] Among them, the adjustment feedback index refers to the comprehensive index parameter formed after quantification of various feedback information related to the tightness of the comprehensive intelligent helmet during the adjustment process (including the deviation data between the target tightness position and the actual tightness position, the adjustment execution status data collected by the sensor in real time, the operator's somatosensory feedback data on the tightness, etc.); the target tightness position refers to the ideal tightness position parameter of the helmet pre-set according to the working scene and the adaptation requirements of the human body, which is used to guide the adjustment execution. For example, in order to ensure stability during high-altitude operations, Set as "hat strap retracts to 3cm from the initial position", the corresponding numerical looseness code is 0.6 (coding rules are customized); the actual tightness position refers to the current tightness state parameter of the helmet collected in real time by the sensor, and Compare and calculate the adjustment deviation. For example, the sensor detects that the actual shrinkage of the hat strap is 2.5cm, which corresponds to the looseness code 0.5. The deviation of (code 0.6) is used to trigger adjustment compensation; the reference tightness position refers to the universal tightness benchmark parameter determined based on a large amount of standard operation human body adaptation data, which is used as a reference for deviation calculation. For example, if 100 sets of comfortable operation data are counted, Set as "hat strap shrink 2cm" (code 0.4), when the actual position deviates, combined with Quantify the degree of deviation.

[0136] Furthermore, the analysis of the adjustment feedback index in the instruction feedback parameter can be achieved through a fuzzy logic algorithm, such as: using MATLAB's Fuzzy Logic Toolbox to establish an evaluation model to obtain the adjustment feedback index; the determination of the target tightness position corresponding to the smart helmet can be achieved through a pressure distribution optimization method, such as: using ANSYS Mechanical to perform head mold pressure simulation analysis to obtain the target tightness position; the determination of the actual tightness position corresponding to the smart helmet can be achieved through strain gauge measurement technology, such as: collecting elastic band strain data through the HX711 module to obtain the actual tightness position; the analysis of the reference tightness position corresponding to the target tightness position and the actual tightness position can be achieved through a difference weighted average method, such as: applying Python's numpy library to calculate the optimal compromise position to obtain the reference tightness position.

[0137] As another embodiment of the present invention, the tightness adjustment index corresponding to the smart helmet is calculated as follows:

[0138]

[0139] in, Indicates the tightness adjustment index corresponding to the smart helmet, represents the system efficiency factor, Indicates the target tightness position, Indicates the actual tightness position. Indicates the reference tightness position, represents the error smoothing constant, represents the time decay coefficient, Indicates the actual feedback delay time, Indicates the maximum allowed delay time, represents the interference sensitivity coefficient, Indicates changes in ambient light. Indicates the maximum expected environmental disturbance.

[0140] In detail, the system efficiency factor refers to the correction coefficient that characterizes the execution efficiency of the intelligent helmet adjustment system, which is related to the hardware response speed and algorithm optimization. The value is calibrated based on historical adjustment data. If the system is tested and running stably, Set to 1.2, if the hardware is aging, It can be reduced to 0.9, which weakens the adjustment efficiency. The error smoothing constant is used to weaken the interference of small deviations on the calculation during the adjustment process, and avoid over-adjustment caused by high-frequency fluctuations of the sensor. For example, Set to 0.1, when the actual and target positions deviate by 0.05 (encoding difference), the error can be smoothed by the formula to maintain the stability of the regulation. The time decay coefficient is a coefficient that measures the degree of influence of feedback delay on the regulation effect. The larger the λ, the more significant the attenuation of the regulation effect caused by the delay. For example, if λ is set to 0.8, if the feedback delay is 1 second ( ), maximum allowed delay Seconds, time decay term It will reduce the adjustment index and reflect the negative impact of delay. The actual feedback delay time refers to the time interval from triggering the adjustment command to obtaining the looseness and tightness status feedback, reflecting the system response speed. For example, after the command is issued, the sensor returns data in 300 milliseconds. If the network is congested, the delay may increase to 0.8 seconds, affecting the timeliness of the adjustment. The maximum allowable delay time refers to the upper limit of the feedback delay tolerance set based on system stability and operation safety requirements. If it exceeds the upper limit, the risk of adjustment failure will increase dramatically. For example, to ensure real-time performance, Set to 0.5 seconds, if seconds, a timeout warning needs to be triggered and the adjustment strategy needs to be adjusted; the interference sensitivity coefficient refers to the coefficient that quantifies the influence of environmental interference (such as light, vibration) on the tightness adjustment. The larger the ω is, the more attention is paid to the adjustment deviation caused by environmental interference. For example, in a strong light scene, ω is set to 0.6, and when the ambient light change ΔI=200lux, it will pass The term weakens the adjustment index and reflects the influence of interference. The ambient light change refers to the real-time fluctuation value of the light intensity in the working environment, which is input into the formula as an interference factor to reflect the influence of the environment on the adjustment. For example, if the working area changes from 1000 lux (initial) to 1500 lux, ΔI=500 lux. , will trigger the calculation of the interference correction term and adjust the regulation index; the maximum expected environmental interference refers to the extreme environmental interference threshold predicted based on the working scene, which is used to normalize the impact of ambient light changes, such as outdoor work, Set to 2000lux, when the actual ΔI=1500lux, , combined with ω, calculate the degree of weakening of the regulation index by interference and limit the impact range of extreme interference.

[0141] S5. Based on the tightness adjustment index, dynamically adjust the unit working parameters corresponding to the posture adjustment unit in the smart safety helmet, generate a comprehensive operation record corresponding to the smart safety helmet based on the unit working parameters, and extract the safety performance data in the comprehensive operation record. Based on the performance data, formulate an adaptive adjustment plan corresponding to the smart safety helmet.

[0142] Based on the tightness adjustment index, the present invention dynamically adjusts the unit working parameters corresponding to the posture adjustment unit in the smart safety helmet, so that the posture adjustment can accurately adapt to the current tightness of the helmet body, avoid posture monitoring and adjustment deviations due to uncomfortable tightness, enhance the adaptability of the smart safety helmet to complex working scenarios, and lay a solid foundation for safety protection from the hardware adaptation dimension.

[0143] Among them, the posture adjustment unit refers to a functional module in the smart safety helmet used to monitor and adjust the operator's head posture. It integrates sensors and actuators, can collect posture data and perform adjustment actions, for example, the built-in gyroscope and accelerometer monitor the head tilt angle (such as 0-90° range) and shaking frequency (0-5 times per second). When it detects that the head tilts forward for more than 30° for more than 5 seconds, the motor drives the support structure inside the helmet to fine-tune (adjustment range 0-10mm) to assist the operator in maintaining a safe and comfortable posture; the unit working parameters refer to the operating settings of the posture adjustment unit when performing posture adjustment, such as adjustment force, frequency, threshold, etc., which determine the adjustment effect. For example, the unit working parameters are set to "when the head tilt angle exceeds 15°, it will be called back at an amplitude of 2° per second, and the adjustment frequency is once every 5 seconds". By dynamically adjusting these parameters, it can adapt to the posture control needs under different tightness states.

[0144] As an embodiment of the present application, the unit working parameter corresponding to the posture adjustment unit in the smart safety helmet is dynamically adjusted based on the tightness adjustment index, including: analyzing the head pressure degree corresponding to the tightness adjustment index; analyzing the adjustment fluctuation period corresponding to the head pressure degree; dividing the tightness state stage corresponding to the adjustment fluctuation period; counting the unit response parameter in the tightness state stage; and dynamically adjusting the unit working parameter corresponding to the posture adjustment unit based on the unit response parameter.

[0145] The head pressure degree refers to a pressure index acting on the head of the operator caused by the tightness state of the safety helmet, which is collected by a pressure sensor and reflects the compression intensity of the head caused by the tightness adjustment. For example, after the tightness adjustment, the sensor detects that the head pressure changes from 20 kPa to 30 kPa, and the change in the value reflects the change in the head pressure degree. Excessive pressure may affect the comfort and safety of the operation, and is the basis for adjusting the posture adjustment. The adjustment fluctuation period refers to the time interval in which the head pressure degree changes periodically with time during the tightness adjustment process, and reflects the rhythmic nature of the adjustment action. For example, after each execution of the tightness fine adjustment (such as a 1 cm contraction of the hat band), the pressure rises from 25 kPa to 32 kPa, and then falls to 28 kPa stably after 10 seconds. The cycle of pressure change for about 10 seconds is the adjustment fluctuation period, which is used to analyze the stability of the adjustment. The tightness state stage refers to different tightness state intervals divided according to the change characteristics of the pressure degree in the adjustment fluctuation period, and reflects the stage nature of the adjustment process. For example, in one adjustment period, the pressure rising stage (25-32 kPa) is the “pre-tightening adjustment stage”, and the pressure stable stage (28-30 kPa) is the “fitting maintenance stage”. Different stages correspond to different posture adjustment requirements. The unit response parameter refers to a quantitative index of the posture adjustment unit responding to the change of the head posture in the tightness state stage, including response time, adjustment amplitude, etc. For example, in the “pre-tightening adjustment stage”, the posture adjustment unit detects that the head tilt angle changes from 10° to 15°, and starts adjustment within 2 seconds to adjust the angle to 12°. The 2-second response time and 3° adjustment amplitude are the unit response parameters.

[0146] Furthermore, the analysis of the head pressure level corresponding to the tightness adjustment index can be achieved through a pressure mapping algorithm, such as: using a finite element analysis method to calculate the pressure distribution of the head contact surface, thereby obtaining the head pressure level; the analysis of the adjustment fluctuation period corresponding to the head pressure level can be achieved through a Fourier transform method, such as: using an FFT algorithm to convert the pressure time domain signal into a frequency domain feature, thereby obtaining the adjustment fluctuation period; the division of the tightness state stages corresponding to the adjustment fluctuation period can be achieved through a K-means clustering algorithm, such as: performing state classification based on the pressure fluctuation amplitude and duration, thereby obtaining the tightness state stage; the statistics of the unit response parameters in the tightness state stage can be achieved through a time series analysis method, such as: applying an ARIMA model to quantify the action response delay of the adjustment unit, thereby obtaining the unit response parameters; the dynamic adjustment of the unit working parameters corresponding to the posture adjustment unit can be achieved through a PID control algorithm, such as: calculating the proportional-integral-differential control quantity based on the real-time feedback parameters, thereby obtaining the unit working parameters.

[0147] Based on the working parameters of the unit, the present invention generates a comprehensive operation record corresponding to the smart safety helmet and extracts safety performance data from the comprehensive operation record. It can integrate the working parameters of the posture adjustment unit with the actual operation performance, and can accumulate safety experience from the dimension of the entire operation process, and continuously improve the protection accuracy and safety assurance capabilities of the smart safety helmet.

[0148] The comprehensive operation record refers to a complete operation file formed by continuously collecting and integrating various key data of the smart helmet during the operation process, covering information such as unit working parameters, posture data, environmental parameters and control instructions. For example, the record includes: operation time of 8 hours, average response time of the posture adjustment unit of 0.8 seconds, maximum adjustment range of 10mm, ambient temperature fluctuation range of 25-32°C, triggering of secondary warnings 3 times, average tension adjustment index of 0.75, etc., which comprehensively presents the equipment status and environmental changes during the entire operation process; the safety effectiveness data refers to quantitative indicators extracted from the comprehensive operation record for evaluating the safety protection effect of the smart helmet, reflecting the actual effectiveness of the equipment in risk warning, posture adjustment, etc. For example, the extracted data includes: warning accuracy rate of 92% (all 3 warnings were real risks), posture adjustment success rate of 88% (10 out of 12 adjustments made the posture stability coefficient return to above 0.6), and average risk response delay of 0.5 seconds. These data directly reflect the equipment's ability to ensure operation safety. Optionally, the generation of the comprehensive operation record corresponding to the smart helmet can be achieved through multi-source data fusion technology, such as: using Apache The Kafka stream processing platform integrates physiological monitoring and environmental sensor data to obtain comprehensive operation records; the extraction of safety efficiency data from the comprehensive operation records can be achieved through feature engineering methods, such as: using the PCA principal component analysis algorithm to reduce the dimension and extract key performance indicators to obtain safety efficiency data.

[0149] Furthermore, based on the performance data, the present invention formulates an adaptive adjustment plan corresponding to the smart safety helmet, which can enable the plan to accurately match the safety requirements and equipment performance in actual operations, improve the adaptability and effectiveness of the adjustment plan, and at the same time provide a data-driven direction for the iterative upgrade of the smart safety helmet, fundamentally enhancing its safety assurance capabilities in complex operating scenarios.

[0150] The adaptive adjustment scheme refers to a set of systematic optimization strategies that can dynamically adjust operation logic and parameters, with safety performance data as the core basis, for the performance of the intelligent safety helmet in different work scenarios, covering multiple functional dimensions such as posture monitoring accuracy, early warning response strength, tightness adjustment range, and environmental adaptation threshold. It can automatically switch and adapt modes according to real-time work conditions. For example, if the comprehensive work record shows that in the "strong wind + high altitude" scenario, the frequency of posture stability coefficient below 0.5 is high (8 times per hour), and the current posture adjustment unit has an average response delay of 1.5 seconds (1 second beyond the safety standard), and the tightness adjustment is prone to over-tightness (pressure exceeding 40 kPa) when the wind speed is ≥10 m / s, then the adaptive adjustment scheme can be set as follows: when the wind speed ≥8 m / s and the working height ≥5 meters are detected, the response threshold of the posture adjustment unit is set to 0.6, the response speed is increased to 0.8 seconds, the maximum pressure limit of the tightness adjustment is lowered to 35 kPa, and the environmental compensation coefficient is simultaneously increased from 0.3 to 0.5. Through multi-parameter linkage adjustment, the safety performance data of the device in this scenario is optimized to the target range, improving the accuracy and adaptability of overall protection. Optionally, the adaptive adjustment scheme corresponding to the intelligent safety helmet can be realized through a closed-loop optimization control framework, such as using the model predictive control (MPC) algorithm combined with physiological feedback and environmental parameter dynamic optimization to obtain the adaptive adjustment scheme.

[0151] Compared with the problems described in the background art, the present application can capture the body state of the operator and the change of the surrounding environment in real time by acquiring physiological data and environmental data of the intelligent safety helmet worn by the target operator, provide data support for accurate judgment of physiological stress state, realize comprehensive perception of the operation scene, and lay a reliable data foundation for subsequent adaptive adjustment and safety evaluation. The present application can break the isolation of single sensor data by marking the dynamic coupling features corresponding to the posture sensor and the light sensor in the operation perception network, reveal the correlation law of the two in different operation scenes, improve the comprehensive perception ability of complex operation conditions, lay a foundation for subsequent extraction of key feature parameters, enhance the adaptability and response accuracy of the intelligent safety helmet to the dynamic operation environment, and further, based on the operation safety value, simulate the operation risk environment of the intelligent safety helmet under the sudden condition, extend the static safety evaluation to dynamic risk deduction, expose potential safety hazards in advance, help to improve the response resilience of the intelligent safety helmet to complex dangers, from passive protection to active prediction, strengthen the whole-process guarantee of operation safety. Further, the present application generates the dynamic regulation instruction corresponding to the intelligent safety helmet by integrating the adaptive adjustment logic and the preset multi-level warning rule, can organically integrate real-time adjustment demand and hierarchical warning mechanism, can strengthen the gradient of safety warning through multi-level warning, improve the comprehensive efficiency of the instruction, make the intelligent safety helmet form synergy in response timeliness and risk warning intensity, and comprehensively enhance the dynamic management and control ability to operation safety. Finally, based on the tightness adjustment index, the present application dynamically adjusts the unit working parameters corresponding to the posture adjustment unit in the intelligent safety helmet, can make the posture adjustment accurately adapt to the current hat body tightness state, avoid posture monitoring and adjustment deviation caused by tightness inadaptation, enhance the adaptability of the intelligent safety helmet to complex operation scenes, and consolidate the safety protection foundation from the hardware adaptation dimension. Therefore, the adaptive adjustment recording method and system of the intelligent safety helmet provided by the embodiment of the present application can improve the wearing comfort of the intelligent safety helmet and enhance the operation safety protection ability.

[0152] As Figure 3 shown, it is a functional module diagram of the adaptive adjustment recording system of the intelligent safety helmet.

[0153] The adaptive adjustment recording system 200 of the intelligent safety helmet can be installed in an electronic device. According to the functions to be realized, the adaptive adjustment recording system of the intelligent safety helmet can include a network construction module 201, a safety value calculation module 202, a logic construction module 203, an index calculation module 204 and a scheme development module 205. The modules of the present application can also be called units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, and are stored in the memory of the electronic device.

[0154] In the embodiments of the present application, the functions of each module / unit are as follows:

[0155] The network construction module 201 is configured to acquire physiological data and environmental data of the smart safety helmet when worn by a target worker, determine physiological stress states of the smart safety helmet under different working conditions based on the physiological data and the environmental data, and construct a working perception network corresponding to the smart safety helmet based on the physiological stress states.

[0156] The safety value calculation module 202 is configured to mark dynamic coupling features corresponding to posture sensors and light sensors in the working perception network, extract a posture stability coefficient and an environmental interference threshold in the dynamic coupling features, and calculate an operation safety value of the smart safety helmet under comprehensive work based on the posture stability coefficient and the environmental interference threshold.

[0157] The logic construction module 203 is configured to simulate a working risk environment of the smart safety helmet under a sudden condition based on the operation safety value, and construct adaptive adjustment logic corresponding to the smart safety helmet according to the working risk environment.

[0158] The index calculation module 204 is configured to integrate the adaptive adjustment logic and a plurality of preset warning rules to generate a dynamic regulation instruction corresponding to the smart safety helmet, acquire an instruction feedback parameter after execution of the dynamic regulation instruction, and calculate a tightness adjustment index corresponding to the smart safety helmet based on the instruction feedback parameter.

[0159] The scheme formulation module 205 is configured to dynamically adjust a unit working parameter corresponding to a posture adjustment unit in the smart safety helmet based on the tightness adjustment index, generate a comprehensive work record corresponding to the smart safety helmet based on the unit working parameter, extract safety efficiency data in the comprehensive work record, and formulate an adaptive adjustment scheme corresponding to the smart safety helmet based on the efficiency data.

[0160] In detail, the modules in the adaptive adjustment record system 200 of the smart safety helmet in the embodiments of the present application use the same technical means as the adaptive adjustment record method of the smart safety helmet in the above-mentioned Figure 1 , and can produce the same technical effects, which will not be described here.

[0161] It is obvious for those skilled in the art that the present application is not limited to the details of the above-mentioned exemplary embodiments, and can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0162] Finally, it should be noted that the above embodiments, the deletion of any one of the above embodiments does not affect the technical solutions of other embodiments, the above embodiments are only used to illustrate the technical solutions of the present application but not limit, although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalent replaced without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A self-adaptive adjustment and recording method for a smart helmet, characterized in that: The method comprises: Acquiring physiological data and environmental data of the smart helmet when worn by a target worker, determining the physiological stress state of the smart helmet under different working conditions based on the physiological data and the environmental data, and constructing a work perception network corresponding to the smart helmet based on the physiological stress state; Marking dynamic coupling features corresponding to the posture sensor and the light sensor in the operation perception network, extracting a posture stability coefficient and an environmental interference threshold from the dynamic coupling features, and calculating an operational safety value of the smart helmet under comprehensive operation based on the posture stability coefficient and the environmental interference threshold; Based on the operational safety value, simulating the operational risk environment of the smart helmet under an emergency situation, and constructing adaptive adjustment logic corresponding to the smart helmet according to the operational risk environment; Integrating the adaptive adjustment logic with preset multi-level warning rules to generate dynamic control instructions corresponding to the smart helmet, obtaining instruction feedback parameters after the dynamic control instructions are executed, and calculating the tightness adjustment index corresponding to the smart helmet based on the instruction feedback parameters; Based on the tightness adjustment index, the unit working parameters corresponding to the posture adjustment unit in the smart safety helmet are dynamically adjusted. Based on the unit working parameters, a comprehensive operation record corresponding to the smart safety helmet is generated, and the safety performance data in the comprehensive operation record is extracted. Based on the performance data, an adaptive adjustment plan corresponding to the smart safety helmet is formulated.

2. The method for self-adapting and recording a smart helmet according to claim 1, wherein: The step of constructing a work perception network corresponding to the smart helmet based on the physiological stress state includes: Analyzing the state response stage corresponding to the physiological stress state; identifying characteristic physiological fluctuation segments in the state response phase; Analyzing the operation risk level corresponding to the characteristic physiological fluctuation segment; Formulate operation monitoring rules corresponding to the operation risk level; Based on the operation monitoring rules, a operation perception network corresponding to the smart safety helmet is constructed.

3. The self-adaptive adjustment and recording method of a smart helmet according to claim 1, characterized in that: The marking of the dynamic coupling characteristics corresponding to the posture sensor and the light sensor in the operation perception network includes: Acquire a posture data sequence corresponding to a posture sensor and a light sensing data sequence corresponding to a light sensing sensor in the operation perception network; Synchronously aligning the time domain sampling points corresponding to the posture data sequence and the light sensing data sequence; Based on the time domain sampling points, constructing a posture-light joint distribution map corresponding to the posture sensor and the light sensor; Extracting time-varying fluctuation points in the posture-illumination joint distribution map; Based on the time-varying fluctuation points, dynamic coupling features corresponding to the posture sensor and the light sensor in the operation perception network are marked.

4. The self-adaptive adjustment and recording method of a smart helmet according to claim 1, characterized in that: The calculating, based on the posture stability coefficient and the environmental interference threshold, the operational safety value of the smart helmet under comprehensive operation includes: Analyzing the attitude sensitivity factor corresponding to the attitude stability coefficient; Obtaining an environmental compensation coefficient and a real-time value of environmental disturbance corresponding to the environmental interference threshold; Combining the posture sensitivity factor, the environmental compensation coefficient, and the real-time value of the environmental disturbance, the operational safety value of the smart helmet under comprehensive operation is calculated using the following formula: in, Indicates the operational safety value of the smart helmet under comprehensive operation, represents the safety calibration constant, represents the posture sensitivity factor, represents the attitude stability coefficient, represents the environmental compensation coefficient, Indicates the real-time value of environmental disturbance, represents the environmental interference threshold, represents the dynamic coupling gain, represents the cumulative risk, Indicates the lower limit of risk.

5. The self-adaptive adjustment and recording method of a smart helmet according to claim 1, characterized in that: The simulating, based on the operational safety value, an operational risk environment of the smart helmet in an emergency situation includes: Analyze the safety threshold baseline corresponding to the operation safety value; Determining a typical emergency scenario in which the operator wearing the smart helmet is located based on the safety threshold baseline; Analyze the trigger probability vector corresponding to the typical emergency scenario; quantifying an instantaneous pressure parameter corresponding to the smart helmet based on the trigger probability vector; Based on the instantaneous pressure parameters, the operating risk environment of the smart safety helmet in an emergency situation is simulated.

6. The self-adaptive adjustment and recording method of a smart helmet according to claim 1, characterized in that: The step of constructing the adaptive adjustment logic corresponding to the smart helmet according to the operational risk environment includes: Extract key risk factors from the operational risk environment; Based on the key risk factors, setting the adjustment priority corresponding to the smart helmet; Obtaining a preset adjustment plan that matches the adjustment priority; Analyzing the logical triggering conditions in the preset adjustment plan; Based on the logic triggering conditions, an adaptive adjustment logic corresponding to the smart helmet is constructed.

7. The method for self-adapting and recording a smart helmet according to claim 1, wherein: The integration of the adaptive adjustment logic and the preset multi-level warning rules to generate dynamic control instructions corresponding to the smart helmet includes: Extracting key condition elements in the adaptive adjustment logic; Clarify the warning execution method corresponding to the preset multi-level warning rules; Based on the key condition elements and the warning execution mode, constructing rule decision items corresponding to the smart helmet; Simulate typical warning scenarios corresponding to the rule decision items; Based on the typical warning scenario, dynamic control instructions corresponding to the smart helmet are generated.

8. The method for self-adapting and recording a smart helmet according to claim 1, wherein: The obtaining of the instruction feedback parameter after the execution of the dynamic control instruction includes: Collecting raw response data from the posture sensor and the light sensor when the dynamic control instruction is executed; Performing denoising processing on the original response data to obtain denoised response data; extracting a stability indicator from the denoised response data; Based on the stability index and the preset environmental interference threshold, the instruction feedback parameters of the dynamic control instruction after execution are analyzed.

9. The self-adaptive adjustment and recording method of a smart helmet according to claim 1, characterized in that: The dynamically adjusting the unit working parameters corresponding to the posture adjustment unit in the smart helmet based on the tightness adjustment index includes: Analyzing the head pressure level corresponding to the tightness adjustment index; Analyzing the adjustment fluctuation period corresponding to the head pressure level; Dividing the adjustment fluctuation cycle into loose and tight state stages; Counting the unit response parameters in the loose and tight state stages; Based on the unit response parameters, the unit working parameters corresponding to the posture adjustment unit are dynamically adjusted.

10. An adaptive adjustment and recording system for a smart helmet, characterized in that: The system comprises: a network construction module for acquiring physiological data and environmental data of the smart helmet when worn by a target worker, determining the physiological stress state of the smart helmet under different working conditions based on the physiological data and the environmental data, and constructing a work perception network corresponding to the smart helmet based on the physiological stress state; a safety value calculation module, configured to mark dynamic coupling features corresponding to the posture sensor and the light sensor in the operation perception network, extract a posture stability coefficient and an environmental interference threshold from the dynamic coupling features, and calculate an operational safety value of the smart helmet under comprehensive operation based on the posture stability coefficient and the environmental interference threshold; a logic construction module, configured to simulate, based on the operational safety value, an operational risk environment of the smart helmet under an emergency situation, and construct an adaptive adjustment logic corresponding to the smart helmet according to the operational risk environment; an index calculation module, configured to integrate the adaptive adjustment logic with preset multi-level warning rules, generate dynamic control instructions corresponding to the smart helmet, obtain instruction feedback parameters after the dynamic control instructions are executed, and calculate the tightness adjustment index corresponding to the smart helmet based on the instruction feedback parameters; A plan formulation module is used to dynamically adjust the unit working parameters corresponding to the posture adjustment unit in the smart safety helmet based on the tightness adjustment index, generate a comprehensive operation record corresponding to the smart safety helmet based on the unit working parameters, and extract safety performance data from the comprehensive operation record, and formulate an adaptive adjustment plan corresponding to the smart safety helmet based on the performance data.

Images