Underwater pressure intelligent monitoring and feedback system for diving assistance

Abstract

The invention discloses an underwater pressure intelligent monitoring and feedback system for diving assistance, which relates to the technical field of diving and comprises an acquisition module, a microprocessor, a display module, an alarm module and a communication module, the acquisition module is used for acquiring underwater real-time data of the diving equipment during diving through a sensor, and the sensor is installed in the diving equipment; according to the underwater pressure intelligent monitoring and feedback system for diving assistance, a display module displays processed key parameters, an alarm module gives out a sound-light alarm under an abnormal condition to remind a diver to take measures, and a communication module sends state and position information to water surface monitoring equipment in real time; through multi-source data fusion and intelligent analysis, comprehensive and real-time safety monitoring and feedback are provided for divers, and the safety and reliability of diving activities are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of diving technology, and in particular to an underwater pressure intelligent monitoring and feedback system for diving assistance. Background Art

[0002] Diving is an activity carried out in underwater environments such as oceans and lakes, involving a variety of safety risks. Divers are affected by various factors such as pressure, temperature, and gas composition in underwater environments, and may face dangerous situations such as decompression sickness, hypoxia, heat stroke, or hypothermia. Therefore, real-time monitoring and feedback of changes in the diving environment and the physical condition of divers are crucial to ensure diving safety.

[0003] Traditional diving monitoring equipment usually relies on a single or limited number of sensors, which limits the types and real-time nature of the data collected. Although diving equipment can provide basic depth and time information, it cannot monitor the changes in multiple parameters in real time, such as underwater pressure, temperature, gas composition, and the movement status of divers. In addition, traditional equipment usually lacks the function of in-depth analysis and intelligent feedback of data, and can only provide limited alarm information in emergency situations, and cannot predict potential risks in advance. Summary of the invention

[0004] In order to solve the above technical problems, the present invention is implemented through the following technical solutions: an underwater pressure intelligent monitoring and feedback system for diving assistance, comprising a collection module, a microprocessor, a display module, an alarm module and a communication module; the collection module is used to collect real-time underwater data of the diving equipment during diving through a sensor, wherein the sensor is installed in the diving equipment; The microprocessor is used to receive the real-time data collected by the collection module, process and analyze the real-time data, predict the physical condition and diving risk of the diver based on the diving comprehensive analysis model, and generate a prediction result. The diving comprehensive analysis model includes a Kalman filter model, a fuzzy logic model and a neural network model; The display module is used to display the processed pressure, depth, temperature, gas composition, position and motion parameters in real time; The alarm module is used to send out an audible and visual alarm when an abnormal situation is detected, reminding the diver to take corresponding measures; The communication module is used to send the diver's status and location information to the monitoring equipment on the surface of the water so as to facilitate rescue in emergency situations.

[0005] Preferably, the acquisition module includes: a pressure sensor, a depth sensor, a temperature sensor, a gas sensor, a positioning sensor, and a motion sensor: the pressure sensor is used to monitor the underwater pressure changes in real time and transmit the pressure data to the microprocessor; the depth sensor is used to determine the diving depth by measuring the water pressure and transmit the depth data to the microprocessor; the temperature sensor is used to monitor the underwater temperature and transmit the temperature data to the microprocessor; the gas sensor is used to detect the underwater gas composition, including the oxygen content and the carbon dioxide content, and transmit the gas composition data to the microprocessor; the positioning sensor is used to determine the position of the diver and transmit the position information to the microprocessor; the motion sensor is used to monitor the diver's motion state, including speed and acceleration, and transmit the motion data to the microprocessor; wherein the real-time data transmission of each of the sensors adopts low-power Bluetooth technology to reduce energy consumption and extend the battery life of the device; the data uses encryption technology during transmission to ensure the security and privacy of the data and prevent the data from being intercepted or tampered with during transmission.

[0006] Preferably, the diving comprehensive analysis model is based on comprehensive consideration of the pressure change rate, pressure peak detection and pressure fluctuation frequency, combined with the following algorithm formula to predict the diver's physical condition and diving risk: The diving comprehensive analysis model is based on comprehensive consideration of the pressure change rate, pressure peak detection and pressure fluctuation frequency, combined with the following algorithm formula to predict the diver's physical condition and diving risk: The pressure change rate is calculated using the following formula: ; Indicates the pressure value at time t; t, indicates the pressure time point; The formula for calculating the average rate of change calculated at multiple time points is: ; m represents the number of time points; let the pressure sequence be P= ; Find the maximum pressure value in the pressure sequence; the maximum value ; Minimum pressure ; Find the minimum pressure value in the pressure sequence; Pressure fluctuation frequency calculation formula: ; F(k) represents the discrete Fourier transform result of the sequence at frequency index k; Represents the nth value in the pressure sequence; N represents the number of points in the input sequence, that is, the length of the sequence; k represents the frequency index, k=0,1,2,...n; N-1 represents different frequency components; represents the complex exponential function and also represents the basis function of discrete Fourier transform, where i is the imaginary unit; calculate To obtain the power of each frequency component, the power reflects the intensity of the frequency component in the pressure signal; is the main frequency of pressure fluctuations; The calculation formula of the comprehensive index is as follows: ; S represents a comprehensive index, which comprehensively evaluates the performance of the pressure sensor and the complexity of the pressure state by combining information from three aspects: pressure change rate, pressure peak detection, and pressure fluctuation frequency; It means that the influence of pressure change rate on comprehensive index can be adjusted; in is the weight coefficient of the pressure change rate, is the absolute value of the rate of pressure change, is the maximum value of the pressure change rate; : Indicates the impact of adjusting the pressure peak detection on the comprehensive index; in, is the weight coefficient for pressure peak detection; It is the preset pressure range of the system; Indicates the effect of adjusting the pressure fluctuation frequency on the comprehensive index; in, is the weight coefficient of the pressure fluctuation frequency, is the maximum value of the pressure fluctuation frequency, is the main frequency of pressure fluctuations; Among them, the three weight coefficients satisfy ; Its function is to adjust the importance of different indicators in the comprehensive indicators according to actual needs; The microprocessor includes a data processing unit and a data analysis unit; the data processing unit receives real-time data from the sensor and pre-processes the real-time data to improve the accuracy and consistency of the real-time data; during the pre-processing of the real-time data by the data processing unit, the data processing unit is also used to quickly analyze the real-time data and generate a trigger event; The data processing unit receives real-time data from the sensor and pre-processes the real-time data: Firstly, the received real-time data is binary decoded to extract digital data; Then, a cyclic redundancy check is performed on the digital data to obtain a verified verification data set; Then, a median filter is applied to remove the burst noise in the verification data set to obtain a quasi-data set; Then, the standard value is set to calibrate the data in the alignment data set to obtain calibration data; Convert the calibrated calibration data into required format data, and compress the continuous format data using differential coding to obtain compressed data; then organize the compressed data into a data packet in JSON format; The data analysis unit uses a Kalman filter model to fuse and estimate the state of the pre-processed data packets to eliminate the interference and noise of the underwater environment on the data, and generates a state estimate after the fusion of the data packets for further analysis; The data analysis unit uses the Kalman filter model to fuse and estimate the state of the data packets: First, the key parameters of the Kalman filter are initialized, including the initial state of the system, such as pressure, depth, temperature, and the initial state estimate and error covariance matrix are set. The state transfer matrix, control matrix, measurement matrix, and covariance matrix of process noise and measurement noise are defined. Based on the state estimation at the previous moment and the state transition equation of the system, predict the system state at the current moment. This step also includes the covariance matrix of the prediction error to reflect the uncertainty of the state prediction. The weight of fusing the predicted state with the actual measurement value. It is determined by calculating the relationship between the prediction error and the measurement error. This step is the core of Kalman filtering, which makes the fused state estimation more accurate; By combining the actual measured value with the predicted state as described above, the state estimate at the current moment is updated; this update process corrects the predicted error and generates a new state estimate. At the same time, the error covariance matrix is ​​also updated to reflect the updated uncertainty; ultimately, the Kalman filter output results include the state estimate at the current moment and the corresponding error uncertainty, which can be used for further analysis, control, or system decision support.

[0007] Preferably, the data analysis unit further comprises a fuzzy logic model, and the fuzzy logic model is used to perform fuzzy reasoning and decision making on the data packet; The fuzzy logic model converts the data packet into fuzzy language variables, the fuzzy language variables include good, average and poor, including high, medium and low fuzzy sets, and the specific fuzzy sets are set according to the data type corresponding to the data in the data packet, and based on this, the diver is provided with operation suggestions and warning information, and the operation suggestions and warning information are displayed to the diver through the display module; The fuzzy logic model is used to perform fuzzy reasoning and decision making on data packets: Fuzzification: Establish corresponding high, medium and low fuzzy sets for different types of data in the data packet, and clarify the corresponding fuzzy values ​​in the corresponding fuzzy sets; The input data packets are then converted into membership in the fuzzy sets; Rule base: Define fuzzy rules based on expert knowledge and experience and form a fuzzy rule base, so that the fuzzy rules cover the input combination and its corresponding output decision, which is used to describe the behavior and decision logic of the system; Fuzzy reasoning: Apply the fuzzy rule base, match the fuzzified fuzzy value with the fuzzy rules in the fuzzy rule base, and obtain the output decision of the fuzzy output through the Mamdani reasoning mechanism; Defuzzification: Convert the output decision obtained by fuzzy reasoning back to precise values, based on which the diver can be provided with operational advice and warning information so that specific decisions can be made in the real system. This step uses the maximum membership method to defuzzify and convert the fuzzy output into specific operation quantities. Decision execution: The final accurate value, i.e. the decision result, is used to control specific operations in the control system or to make further data processing; Feedback and adjustment: monitor the matching of the actual output of the system with the expected output decision, and adjust the fuzzy rules or membership functions according to the feedback to optimize the system performance; Iterative processing: The system continuously receives input data and repeatedly performs the above steps, dynamically updating the decision-making process to adapt to changing environmental conditions; Through the above operations, the fuzzy logic model can handle uncertain and ambiguous data, make flexible and accurate decisions, and adapt to complex practical application environments.

[0008] Preferably, the data analysis unit also includes a neural network model; the neural network model is used to learn the relationship between sensor data and the diver's status, fuse pressure, depth, temperature, gas composition, position and motion parameters, predict the diver's physical condition and diving risk, and feed back the prediction results to the diver through a display module and an alarm module.

[0009] Preferably, the microprocessor is also used to trigger an alarm module when abnormal data is received, and the alarm module sends out an audible and visual alarm to alert the diver to potential dangers, such as excessive pressure, low oxygen content or rapid diving; the alarm module can also adjust the intensity and frequency of the alarm according to the level of danger so that the diver can respond quickly.

[0010] Preferably, the communication module is used to send the diver's status and location information to the monitoring equipment on the surface in real time through wireless communication technology; after receiving the information, the monitoring equipment can display the diver's real-time location and status, and issue a rescue instruction in time when it is detected that the diver is in a dangerous state.

[0011] Preferably, the display module includes a screen display unit and a sound prompt unit; the screen display unit is used to display underwater pressure, depth, temperature, gas composition, position and motion parameters in real time, so that divers can understand their own status and surrounding environment at any time; the sound prompt unit is used to provide voice prompts or warnings when the diver's vision cannot focus on the screen, to ensure that the diver can respond to potential dangers in time.

[0012] Preferably, the diving comprehensive analysis model is also used to perform adaptive adjustments based on the diver's historical data, and to improve the accuracy of predicting the diver's status and the reliability of risk assessment by continuously learning and optimizing the diving comprehensive analysis model, thereby improving the diver's safety.

[0013] Preferably, the microprocessor is connected to a cloud platform, which is used to store and analyze historical data of divers; the cloud platform performs big data analysis on the diving data, generates an accurate diving risk model, and transmits the updated model parameters to the microprocessor, which updates its comprehensive diving analysis model accordingly to improve the overall intelligence level of the system; in this way, the system can utilize large amounts of data for learning and optimization, thereby maintaining efficient and safe operation in various diving environments.

[0014] The present invention provides an underwater pressure intelligent monitoring and feedback system for diving assistance, which has the following beneficial effects: 1. This underwater pressure intelligent monitoring and feedback system for diving assistance provides divers with comprehensive and accurate underwater environment monitoring and safety feedback through real-time data collection of multiple sensors and intelligent analysis of multiple models; the Kalman filter, fuzzy logic, and neural network adopted by the system provide technical support in denoising, fuzzy processing, deep learning, and probabilistic inference, respectively, to ensure the accuracy of data and the reliability of risk prediction; in addition, the system's adaptive adjustment function and integration with the cloud platform enable it to continuously learn and optimize, and enhance its application capabilities in complex underwater environments; overall, this system significantly improves the safety of diving activities and the comfort of divers.

[0015] 2. The underwater pressure intelligent monitoring and feedback system for diving assistance introduces multiple models and algorithms. The system can provide divers with accurate and real-time monitoring and feedback in complex underwater environments. Each model focuses on processing specific types of data and risks to ensure that the system can operate effectively in various diving scenarios, thereby improving the safety and comfort of diving. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The present invention is a flowchart of an underwater pressure intelligent monitoring and feedback system for diving assistance. DETAILED DESCRIPTION

[0017] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for the purpose of illustration and description, and are not intended to be exhaustive or to limit the present invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention, and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

[0018] like Figure 1 As shown, the present invention provides a technical solution: an underwater pressure intelligent monitoring and feedback system for diving assistance, comprising a collection module, a microprocessor, a display module, an alarm module and a communication module; the collection module is used to collect real-time underwater data of the diving equipment during diving through a sensor, wherein the sensor is installed in the diving equipment; The microprocessor is used to receive the real-time data collected by the acquisition module, process and analyze the real-time data, predict the physical condition and diving risk of the diver based on the diving comprehensive analysis model, and generate the prediction result. The diving comprehensive analysis model includes Kalman filter model, fuzzy logic model and neural network model; The display module is used to display the processed pressure, depth, temperature, gas composition, position and motion parameters in real time; The alarm module is used to send out sound and light alarms when abnormal conditions are detected, reminding the diver to take corresponding measures; The communication module is used to send the diver's status and location information to monitoring equipment on the surface to facilitate rescue in emergency situations.

[0019] The acquisition module includes: pressure sensor, depth sensor, temperature sensor, gas sensor, positioning sensor, motion sensor: the pressure sensor is used to monitor the underwater pressure changes in real time and transmit the pressure data to the microprocessor; the depth sensor is used to determine the diving depth by measuring the water pressure and transmit the depth data to the microprocessor; the temperature sensor is used to monitor the underwater temperature and transmit the temperature data to the microprocessor; the gas sensor is used to detect the underwater gas composition, including the oxygen content and the carbon dioxide content, and transmit the gas composition data to the microprocessor; the positioning sensor is used to determine the diver's position and transmit the position information to the microprocessor; the motion sensor is used to monitor the diver's motion state, including speed and acceleration, and transmit the motion data to the microprocessor; among them, the real-time data transmission of each sensor adopts low-power Bluetooth technology to reduce energy consumption and extend the battery life of the device; encryption technology is used in the data transmission process to ensure the security and privacy of the data and prevent the data from being intercepted or tampered with during the transmission process. It can monitor the underwater pressure, depth, temperature, gas composition, position and motion parameters in real time, provide divers with comprehensive environmental information, and improve the safety of diving.

[0020] After the system is activated, each sensor module begins to collect real-time data from the diver. When the data processing unit receives the data from each sensor, it begins to perform preliminary data processing: denoising and normalizing the real-time data from the sensor to eliminate noise and environmental interference to ensure the accuracy and consistency of the data; The processed data is uniformly formatted to facilitate subsequent analysis; the pre-processed data is sent to the data analysis unit, where the system fuses the data through the Kalman filter model. The Kalman filter model can effectively remove noise in the data, smooth data fluctuations, and generate stable pressure, depth, temperature, gas composition, position and motion parameters.

[0021] The diving comprehensive analysis model is based on comprehensive consideration of the pressure change rate, pressure peak detection and pressure fluctuation frequency, combined with the following algorithm formula to predict the diver's physical condition and diving risk: The diving comprehensive analysis model is based on comprehensive consideration of the pressure change rate, pressure peak detection and pressure fluctuation frequency, combined with the following algorithm formula to predict the diver's physical condition and diving risk: The pressure change rate is calculated using the following formula: ; Indicates the pressure value at time t; t, indicates the pressure time point; The formula for calculating the average rate of change calculated at multiple time points is: ; m represents the number of time points; let the pressure sequence be ; Find the maximum pressure value in the pressure sequence; the maximum value ; Minimum pressure ; Find the minimum pressure value in the pressure sequence; Pressure fluctuation frequency calculation formula (discrete Fourier transform converts the pressure signal in the time domain to the frequency domain, allowing us to analyze the intensity of different frequency components in the pressure signal): ; Represents the discrete Fourier transform result of the sequence at frequency index k; Represents the nth value in the pressure sequence; N represents the number of points in the input sequence, that is, the length of the sequence; k represents the frequency index, k=0,1,2,...n, N-1 represents different frequency components; represents the complex exponential function and also represents the basis function of DFT, where i is the imaginary unit; calculate To obtain the power of each frequency component, the power reflects the intensity of the frequency component in the pressure signal. is the main frequency of pressure fluctuations; The calculation formula of the comprehensive index is as follows: ; S represents a comprehensive index, which comprehensively evaluates the performance of the pressure sensor and the complexity of the pressure state by combining information from three aspects: pressure change rate, pressure peak detection, and pressure fluctuation frequency; : Indicates that the influence of pressure change rate on comprehensive indicators can be adjusted; in is the weight coefficient of the pressure change rate, is the absolute value of the rate of pressure change, is the maximum value of the pressure change rate; Indicates the impact of adjusting the pressure peak detection on the comprehensive index; in, is the weight coefficient for pressure peak detection; It is the preset pressure range of the system; : Indicates the influence of adjusting the pressure fluctuation frequency on the comprehensive index; in, is the weight coefficient of the pressure fluctuation frequency, is the maximum value of the pressure fluctuation frequency, is the main frequency of pressure fluctuations; Among them, the three weight coefficients satisfy ; Its function is to adjust the importance of different indicators in the comprehensive indicators according to actual needs; Among them, according to the specific use requirements That is, if you think the pressure change rate has the greatest impact on diving safety, you can increase If pressure peak detection is more critical, you can increase If the pressure fluctuation frequency is important, you can increase The value of By continuously inputting and outputting data into the model and combining it with the divers' historical data to train and optimize the diving comprehensive analysis model, the model can learn the relationship between pressure and diving depth, potential dangers and other factors. For example, when the pressure change rate is large and continues to rise, it indicates that the diver is diving quickly or encountering water impact. The neural network outputs corresponding danger warnings based on these characteristics, reminding the diver to take corresponding measures to reduce diving risks. The microprocessor includes a data processing unit and a data analysis unit; the data processing unit receives real-time data from the sensor and pre-processes the real-time data to improve the accuracy and consistency of the real-time data; during the pre-processing of the real-time data by the data processing unit, the data processing unit is also used to quickly analyze the real-time data and generate a trigger event; The data processing unit receives real-time data from the sensor and pre-processes the real-time data: First, the received real-time data is binary decoded to extract valid information and digital data from it; then the digital data is CRC-checked to obtain a check data set after the check, verifying the integrity of the data and ensuring that the data is not damaged or lost during transmission; then a median filter is applied to remove the burst noise in the check data set to improve the reliability and accuracy of the data and obtain an quasi-data set; then a standard value is set to calibrate the data in the quasi-data set to eliminate system errors and obtain calibration data; the calibrated calibration data is converted into the required format data, and differential coding is used to compress the continuous format data to reduce the bandwidth requirements for storage and transmission to obtain compressed data; then the compressed data is organized into a JSON-formatted data packet for subsequent processing or transmission; During the preprocessing of real-time data by the data processing unit, it is also used to quickly analyze the real-time data and generate trigger events: When the temperature data in the collected real-time data exceeds the set temperature threshold as a whole, the collection module will generate a temperature warning data and transmit it to the microprocessor, and the microprocessor will generate a corresponding temperature short warning signal, and map the temperature short warning signal into a temperature short warning flashing reminder box and transmit it to the display module, and remind the diver through the display module, and give the diver an early warning of the current diving temperature; at the same time, the microprocessor will also encode the temperature short warning signal into a temperature short warning ringtone through audio encoding, and transmit it to the alarm module, and the alarm module will send a short and urgent prompt tone to give the diver a sound warning reminder; so that the diver can subjectively judge whether to continue diving under the current temperature warning based on his actual situation, which can help and remind the diver to roughly evaluate whether his own state meets the current diving environment and achieve safe diving; The data analysis unit uses the Kalman filter model to fuse and estimate the state of the pre-processed data packets to eliminate the interference and noise of the underwater environment on the data, and generates a state estimate after the fusion of the data packets for further analysis; The data analysis unit uses the Kalman filter model to fuse and estimate the state of the data packets: First, the key parameters of the Kalman filter are initialized, including the initial state of the system, such as pressure, depth, temperature, etc., and the initial state estimate and error covariance matrix are set. The state transfer matrix, control matrix, measurement matrix, and covariance matrix of process noise and measurement noise are defined. Based on the state estimation at the previous moment and the state transition equation of the system, predict the system state at the current moment. This step also includes the covariance matrix of the prediction error to reflect the uncertainty of the state prediction. The weight of fusing the predicted state with the actual measurement value. It is determined by calculating the relationship between the prediction error and the measurement error. This step is the core of Kalman filtering, which makes the fused state estimation more accurate; During diving, underwater pressure may fluctuate slightly due to environmental factors, but these fluctuations do not mean that the diver is in danger. Through the Kalman filter model, the system filters out these high-frequency noises and only retains data that actually affects the diver's safety. This processing can prevent false alarms and improve the reliability of the system; By combining the actual measured value with the predicted state, the current state estimate is updated; this update process corrects the predicted error and generates a new state estimate. At the same time, the error covariance matrix is ​​updated to reflect the updated uncertainty; finally, the Kalman filter output includes the current state estimate and the corresponding error uncertainty. These outputs can be used for further analysis, control or system decision support; Through the above process, the Kalman filter model can effectively fuse multi-source sensor data and continuously and real-time estimate and update the system state. This process is widely used in navigation systems, automatic control, signal processing and other fields, and can help the system maintain high-precision state tracking in uncertain environments such as diving. When a data packet contains data from no less than two sensors, the raw data collected by these sensors and the data in the preprocessed data packet can be simultaneously input into the Kalman filter model for fusion. The Kalman filter will process these real-time data from different sensors, combine them, and generate a more accurate state estimate.

[0022] The data analysis unit also includes a fuzzy logic model, which is used to perform fuzzy reasoning and decision-making on the data packet; The fuzzy logic model converts the data packet into fuzzy language variables, which include good, average and poor, and provides operation suggestions and warning information to the diver based on the fuzzy language variables. The operation suggestions and warning information are displayed to the diver through the display module. Fuzzy logic models are used to perform fuzzy reasoning and decision making on data packets: 1. Fuzzification Establish corresponding high, medium and low fuzzy sets for different types of data in the data packet, and clarify the corresponding fuzzy values ​​in the corresponding fuzzy sets; Then the input data packet is converted into the membership in the fuzzy set; specifically, the precise input quantity is mapped to the corresponding fuzzy set, and the degree to which the input quantity belongs to different fuzzy sets is determined by the membership function; Example: Taking temperature data as an example, three corresponding fuzzy sets of high temperature, medium temperature and low temperature are established, and the degree to which the input temperature data belongs to different fuzzy sets is determined through the membership function. If the input is temperature, then the temperature value 35°C is fuzzified to the corresponding value in the high temperature set, for example: the membership of high temperature is 0.8, and the membership of medium temperature is 0.2; 2. Rule Base Based on expert knowledge and experience, fuzzy rules are defined and a fuzzy rule base is formed, so that the fuzzy rules cover input combinations and their corresponding output decisions, which are used to describe the behavior and decision logic of the system, such as fuzzy rules in the form of if...then...; Example: Rule 1: If the temperature is high and the depth is high, this is the input combination, then start the cooling system output decision; 3. Fuzzy reasoning Apply the fuzzy rule base, match the fuzzified fuzzy value with the fuzzy rules in the fuzzy rule base, and obtain the output decision of the fuzzy output through the Mamdani reasoning mechanism; Example: Based on the input fuzzy values ​​of high temperature and high humidity, reasoning is performed on multiple related fuzzy rules, and the output decision of cooling system startup is obtained by combining the fuzzy rules; 4. Deblurring Convert the output decision obtained by fuzzy reasoning back to precise values ​​so as to execute specific decisions in the real system. This step uses the maximum membership method to defuzzify and convert the fuzzy output into specific operation quantities. Example: The fuzzy output is the membership of the cooling system startup 0.7, and the defuzzification process determines that the cooling system operates at 70% intensity; 5. Decision execution The final precise value, i.e. the decision result, is used to control specific operations in the control system or make further data processing; for example, controlling actuators, issuing alarms, adjusting system parameters, etc. Example: Based on the defuzzified precise value, the system starts the cooling system and sets the intensity of the cooling system to the defuzzified specific value; 6. Feedback and Adjustment Monitor the matching of the actual output of the system with the expected output decision, and adjust the fuzzy rules or membership functions based on the feedback to optimize the system performance; Example: If the system detects that the cooling effect is insufficient, it will adjust the high temperature membership function so that the system is more inclined to increase the cooling intensity under the same conditions; 7. Iterative Processing The system continuously receives input data and repeatedly executes the above steps, dynamically updating the decision process to adapt to changing environmental conditions; Example: In the case of environmental changes, the system continuously optimizes the cooling strategy through continuous fuzzy reasoning and decision adjustment; Through the above operations, the fuzzy logic model can handle uncertain and ambiguous data, make flexible and accurate decisions, and adapt to complex practical application environments; Processing fuzzy data through fuzzy logic models; for example, underwater temperature changes may have different effects on different divers. Fuzzy logic models convert these temperature data into understandable language variables and provide operational suggestions and warnings to divers based on these variables; For example, during a dive, if the water temperature gradually drops and the diver's movement speed increases, the fuzzy logic model will determine that the diver is rapidly descending to a colder water layer. The system will issue a warning, suggesting that the diver slow down or ascend to avoid physical discomfort or other potential risks caused by the temperature difference.

[0023] The data analysis unit also includes a neural network model; the neural network model is used to learn the relationship between sensor data and the diver's status, integrate pressure, depth, temperature, gas composition, position and motion parameters, predict the diver's physical condition and diving risks, and feed back the prediction results to the diver through the display module and alarm module; if it detects a gradual decrease in oxygen content or an abnormal change in pressure, the system will generate an early warning of potential risks; The composition of the neural network model: Input layer: Receives normalized data from multiple sensors, including pressure, depth, temperature, oxygen content, etc.

[0024] Hidden layers: A series of hidden layers, each containing multiple neurons, are used to extract high-level features of the input data.

[0025] Output layer: predicts the diver’s current status or potential risk, such as safe, needs attention, or dangerous.

[0026] In actual diving, the neural network model can learn the relationship between the diver's physiological responses and environmental changes under different conditions through training with a large amount of historical data. For example, when the neural network detects that the oxygen content is gradually decreasing and the pressure is rising sharply in a short period of time, the system can predict that the diver may be at risk of suffocation or decompression sickness and immediately issue an emergency alarm.

[0027] The microprocessor is also used to trigger the alarm module when it receives abnormal data. The alarm module sends out audible and visual alarms to alert divers to potential dangers, such as excessive pressure, low oxygen content or rapid diving. The alarm module can also adjust the intensity and frequency of the alarm according to the level of danger so that divers can respond quickly.

[0028] The communication module is used to send the diver's status and location information to the monitoring equipment on the surface in real time through wireless communication technology; after receiving the information, the monitoring equipment can display the diver's real-time location and status, and issue rescue instructions in time when it detects that the diver is in a dangerous state.

[0029] The display module includes a screen display unit and a sound prompt unit; the screen display unit is used to display underwater pressure, depth, temperature, gas composition, position and motion parameters in real time, so that divers can understand their own status and surrounding environment at any time; the sound prompt unit is used to provide voice prompts or warnings when the diver's vision cannot focus on the screen, ensuring that the diver can respond to potential dangers in time.

[0030] The diving comprehensive analysis model is also used to make adaptive adjustments based on the diver's historical data. By continuously learning and optimizing the diving comprehensive analysis model, the prediction accuracy of the diver's status and the reliability of risk assessment are improved, thereby improving the diver's safety. The microprocessor is connected to a cloud platform, which is used to store and analyze the diver's historical data. The cloud platform performs big data analysis on the diving data to generate an accurate diving risk model, and transmits the updated model parameters to the microprocessor. The microprocessor updates its diving comprehensive analysis model accordingly to improve the overall intelligence level of the system. The entire system realizes comprehensive monitoring of the diving environment and intelligent feedback of the diver's status through seamless data transmission and processing between various modules. After pre-processing, the data collected by each sensor is fused and denoised through the Kalman filter model, and then deeply analyzed through the fuzzy logic model and the neural network model, and finally generates real-time feedback and early warning, which are notified to the diver through the display and alarm equipment, and the communication module is used to transmit the data to the remote monitoring equipment. With the support of the cloud platform, the system can also adaptively optimize the model parameters according to the diver's historical data to ensure that the system can provide accurate and safe monitoring and feedback in various diving environments.

[0031] The system provides divers with comprehensive and accurate underwater environment monitoring and safety feedback through real-time data collection from multiple sensors and intelligent analysis of multiple models. The Kalman filter, fuzzy logic, and neural network adopted by the system provide technical support in denoising, fuzzy processing, deep learning, and probabilistic inference, respectively, to ensure the accuracy of data and the reliability of risk prediction. In addition, the system's adaptive adjustment function and integration with the cloud platform enable it to continuously learn and optimize, improving its application capabilities in complex underwater environments. Overall, this system significantly improves the safety of diving activities and the comfort of divers, and has broad practical value.

[0032] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field and related fields without creative work should fall within the scope of protection of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention are implemented according to the conventional means in the field unless otherwise specified and limited.

Claims

1. An underwater pressure intelligent monitoring and feedback system for diving assistance, characterized in that: It includes an acquisition module, a microprocessor, a display module, an alarm module and a communication module; The acquisition module is used to collect real-time underwater data of the diving equipment when diving through sensors, wherein the sensors are installed in the diving equipment; The microprocessor is used to receive the real-time data collected by the collection module, process and analyze the real-time data, predict the physical condition and diving risk of the diver based on the diving comprehensive analysis model, and generate a prediction result. The diving comprehensive analysis model includes a Kalman filter model, a fuzzy logic model and a neural network model; The display module is used to display the processed pressure, depth, temperature, gas composition, position and motion parameters in real time; The alarm module is used to send out an audible and visual alarm when an abnormal situation is detected; The communication module is used to send the diver's status and location information to the monitoring equipment on the surface of the water.

2. The underwater pressure intelligent monitoring and feedback system for diving assistance according to claim 1, characterized in that: The acquisition module includes: a pressure sensor, a depth sensor, a temperature sensor, a gas sensor, a positioning sensor, and a motion sensor: the pressure sensor is used to monitor the underwater pressure changes in real time and transmit the pressure data to the microprocessor; the depth sensor is used to determine the diving depth by measuring the water pressure and transmit the depth data to the microprocessor; the temperature sensor is used to monitor the underwater temperature and transmit the temperature data to the microprocessor; the gas sensor is used to detect the underwater gas composition, including the oxygen content and the carbon dioxide content, and transmit the gas composition data to the microprocessor; the positioning sensor is used to determine the position of the diver and transmit the position information to the microprocessor; the motion sensor is used to monitor the diver's motion state, including speed and acceleration parameters, and transmit the motion data to the microprocessor; wherein the real-time data transmission of each of the sensors adopts low-power Bluetooth technology; the data uses encryption technology during transmission.

3. The underwater pressure intelligent monitoring and feedback system for diving assistance according to claim 2, characterized in that: The microprocessor includes a data processing unit and a data analysis unit; the data processing unit receives real-time data from the sensor and pre-processes the real-time data; during the pre-processing of the real-time data by the data processing unit, the data processing unit is also used to quickly analyze the real-time data and generate a trigger event; The data analysis unit uses a Kalman filter model to fuse and estimate the state of the preprocessed data packets, and generates a state estimate after the fusion of the data packets; The data analysis unit uses the Kalman filter model to fuse and estimate the state of the data packets: First, the key parameters of the Kalman filter are initialized, and the initial state estimate and error covariance matrix are set. The state transfer matrix, control matrix, measurement matrix, and covariance matrix of process noise and measurement noise are defined. Based on the state estimation at the previous moment and the state transition equation of the system, predict the system state at the current moment; The weight of fusing the predicted state with the actual measured value is determined by calculating the relationship between the prediction error and the measurement error; By combining the actual measured value with the predicted state, the state estimate at the current moment is updated; ultimately, the result output by the Kalman filter includes the state estimate at the current moment and the corresponding error uncertainty.

4. The underwater pressure intelligent monitoring and feedback system for diving assistance according to claim 3 is characterized in that: The data analysis unit further comprises a fuzzy logic model, wherein the fuzzy logic model is used to perform fuzzy reasoning and decision making on the data packet; The fuzzy logic model converts the data packet into fuzzy language variables, the fuzzy language variables include high, medium and low, and provides operation suggestions and warning information to the diver based on the fuzzy language variables, and the operation suggestions and warning information are displayed to the diver through the display module; The fuzzy logic model is used to perform fuzzy reasoning and decision making on data packets: Establish corresponding high, medium and low fuzzy sets for different types of data in the data packet, and clarify the corresponding fuzzy values ​​in the corresponding fuzzy sets; The input data packets are then converted into membership in the fuzzy sets; Define fuzzy rules based on expert knowledge and experience and form a fuzzy rule base so that the fuzzy rules cover input combinations and their corresponding output decisions; Apply the fuzzy rule base, match the fuzzified fuzzy value with the fuzzy rules in the fuzzy rule base, and obtain the output decision of the fuzzy output through the Mamdani reasoning mechanism; Convert the output decision obtained by fuzzy reasoning back to precise numerical value; The final precise value, i.e. the decision result, is used to control the specific operations in the control system; Monitor the matching of the actual output of the system with the expected output decision, and adjust the fuzzy rules based on the feedback; The system continuously receives input data and repeatedly executes the above steps to dynamically update the decision-making process.

5. The underwater pressure intelligent monitoring and feedback system for diving assistance according to claim 4, characterized in that: The data analysis unit also includes a neural network model; the neural network model is used to learn the relationship between sensor data and the diver's status, fuse pressure, depth, temperature, gas composition, position and motion parameters, predict the diver's physical condition and diving risk, and feed back the prediction results to the diver through a display module and an alarm module.

6. The underwater pressure intelligent monitoring and feedback system for diving assistance according to claim 5, characterized in that: The microprocessor is also used to trigger the alarm module when receiving abnormal data, and the alarm module sends out an audible and visual alarm to remind the diver of potential danger; the alarm module can also adjust the intensity and frequency of the alarm according to the danger level.

7. The underwater pressure intelligent monitoring and feedback system for diving assistance according to claim 6, characterized in that: The communication module is used to send the diver's status and location information to the monitoring equipment on the surface in real time through wireless communication technology; after receiving the information, the monitoring equipment can display the diver's real-time location and status, and issue rescue instructions in time when it detects that the diver is in a dangerous state.

8. The underwater pressure intelligent monitoring and feedback system for diving assistance according to claim 7, characterized in that: The display module includes a screen display unit and a sound prompt unit; the screen display unit is used to display underwater pressure, depth, temperature, gas composition, position and motion parameters in real time; the sound prompt unit is used to provide voice prompts when the diver's vision cannot focus on the screen.

9. The underwater pressure intelligent monitoring and feedback system for diving assistance according to claim 8, characterized in that: The diving comprehensive analysis model is also used to perform adaptive adjustments based on the diver's historical data, by continuously learning and optimizing the diving comprehensive analysis model.

10. The underwater pressure intelligent monitoring and feedback system for diving assistance according to claim 9, characterized in that: The microprocessor is connected to a cloud platform, which is used to store and analyze historical data of divers; the cloud platform performs big data analysis on the diving data, generates an accurate diving risk model, and transmits the updated model parameters to the microprocessor, which updates its diving comprehensive analysis model accordingly to improve the overall intelligence level of the system.

Images