Monomer tank transportation risk early warning method and system based on intelligent sensor

Abstract

The invention discloses a single tank transportation risk early warning method and system based on an intelligent sensor, and relates to the technical field of risk early warning, and the method comprises the steps: collecting data in a single tank for preprocessing, employing a two-dimensional shallow water wave model to calculate liquid fluctuation, and generating iteration sequence data; applying a Hanning window function, calculating spectrum energy distribution according to the spectrum amplitude, extracting primary frequency and secondary frequency data, and calculating the amplitude ratio of the primary frequency to the secondary frequency; according to the method, through coupling of the continuity equation and the momentum equation, the height change and the velocity field distribution of the liquid can be comprehensively described, the dynamic behavior of the liquid in the single tank can be accurately reflected, the dynamic change of the liquid height gradient and the velocity field gradient is considered, and the complex liquid fluctuation phenomenon can be captured; a window function is applied to perform weighting processing on the data to weaken the weight of the data at two ends of the time sequence, so that the middle part of the data contributes more remarkably to the spectrum.

Description

Technical Field

[0001] The present invention relates to the technical field of risk warning, and in particular to a single tank transportation risk warning method and system based on intelligent sensors. Background Art

[0002] With the rapid development of modern logistics and transportation industry, the transportation demand for dangerous goods and liquid goods has increased significantly. As the main container for liquid transportation, the safety and stability of single tanks during transportation are directly related to transportation efficiency and environmental safety. At present, the control measures for liquid transportation risks mainly include physical design enhancement (such as wave-breaking plates, reinforcing rib structures, etc.) and dynamic monitoring based on sensors;

[0003] However, most existing methods only analyze single indicators such as the height or speed of liquid in a single tank, and fail to effectively combine nonlinear dynamic models, spectrum analysis and real-time adjustment mechanisms, thus limiting their ability to dynamically respond to risks in complex transportation environments. In particular, when the liquid in a single tank is subjected to multi-directional disturbances (such as vehicle bumps and sudden braking), the fluctuation behavior often exhibits nonlinear and complex frequency coupling characteristics, which are difficult to capture with traditional single sensors or static computational models. In addition, spectrum analysis often fails to combine time domain characteristics, making it difficult to provide a complete picture of the evolution of fluctuation characteristics over time, reducing the reliability of the early warning system. Summary of the invention

[0004] In view of the problems existing in the above-mentioned existing single tank transportation risk early warning method and system based on intelligent sensors, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is that most of the existing methods remain at the analysis of a single indicator such as the height or speed of the liquid in a single tank, and fail to effectively combine nonlinear dynamic models, spectrum analysis and real-time adjustment mechanisms, thereby limiting the dynamic response capability to risks in a complex transportation environment. In particular, when the liquid in a single tank is subjected to multi-directional disturbances, the fluctuation behavior often exhibits nonlinear and complex frequency coupling characteristics, which are difficult to capture with traditional single sensors or static calculation models. In addition, spectrum analysis often fails to combine time domain characteristics, making it difficult to provide a complete picture of the evolution of fluctuation characteristics over time, thereby reducing the reliability of the early warning system.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a single tank transportation risk early warning method based on intelligent sensors, comprising:

[0007] Collect data from the single tank for preprocessing, use a two-dimensional shallow water wave model to calculate liquid fluctuations, and generate iterative sequence data;

[0008] Apply the Hanning window function, calculate the spectrum energy distribution according to the spectrum amplitude, extract the main frequency and secondary frequency data, and calculate the amplitude ratio of the main frequency to the secondary frequency;

[0009] According to the total energy of the liquid fluctuation, the time step iteration sequence data for dynamically adjusting the damping coefficient and iteratively calculating the total energy is calculated;

[0010] Dynamically adjust the length of the time window, conduct dynamic risk assessment, and issue risk warnings.

[0011] As a preferred solution of the single tank transportation risk early warning method based on intelligent sensors of the present invention, the data in the single tank is collected and preprocessed, including:

[0012] Deploy built-in sensors in single tanks based on single tanks loaded on transport vehicles;

[0013] Built-in sensors include liquid level sensor, pressure sensor and acceleration sensor to collect liquid level, pressure and acceleration data in the single tank;

[0014] The sliding average method is used to eliminate high-frequency noise, smooth the level, pressure and acceleration data, and perform normalization.

[0015] As a preferred solution of the single tank transportation risk early warning method based on intelligent sensors of the present invention, wherein: a two-dimensional shallow water wave model is used to calculate liquid fluctuations and generate iterative sequence data, including:

[0016] The two-dimensional shallow water wave model is used to calculate the liquid fluctuations in the single tank, which are the continuity equation and momentum equation, expressed as:

[0017] ;

[0018] ;

[0019] in represents the instantaneous height of the liquid, represents time, u represents the two-dimensional velocity field of the liquid, g represents the gravitational acceleration, represents the gradient of liquid height, represents the gradient of the velocity field;

[0020] Acquiring an initial liquid height based on a liquid level sensor and determining an initial liquid velocity field in a single tank based on a static state;

[0021] Based on the volume space within the single tank, the number of spatial grid points is determined based on historical data;

[0022] The continuity equation and momentum equation are discretized using the finite difference method FDM;

[0023] The explicit Euler method is used for iterative calculation to update the height and velocity field, which can be expressed as:

[0024] ;

[0025] ;

[0026] in and denote the liquid height at time step n and n+1 respectively, represents the time step, and They represent the product of the liquid height and the x-direction velocity at the grid points (i, j) and (i+1, j) in the single tank, respectively. and They represent the product of the liquid height and the y-direction velocity at the grid points (i, j) and (i, j+1) in the single tank, respectively. represents the velocity field at time step n+1, and Respectively represent the spatial grid step size;

[0027] Compare the height and velocity field calculation results of the current time step with those of the previous time step. When the updated time step difference no longer changes significantly during continuous iterations, stop the iteration and output the time step iteration sequence data of h and u.

[0028] As a preferred solution of the single tank transportation risk early warning method based on intelligent sensors of the present invention, wherein: applying the Hanning window function, calculating the spectrum energy distribution according to the spectrum amplitude, extracting the main frequency and secondary frequency data, and calculating the amplitude ratio of the main frequency to the secondary frequency, including:

[0029] Calculate the spatial average of each time step based on the time step iterative sequence data;

[0030] Applying the Hanning window function to the spatial average height and spatial average velocity field data, the spatial average height and spatial average velocity field data with high frequency noise reduced in the spectrum analysis are obtained;

[0031] The spatial average height and spatial average velocity field data are jointly fast Fourier transformed to obtain the spectrum amplitude of the height and velocity field data respectively, and the spectrum energy distribution is calculated, which is expressed as:

[0032] ;

[0033] in represents the spectral energy distribution of the kth frequency component, and represent the spectral amplitudes of the liquid height and velocity of the kth frequency component respectively;

[0034] based on Output the spectrum diagram and extract the main frequency and secondary frequency data;

[0035] Make the wavelet transform act on the spatial average height simultaneously and the spatial average velocity field , the time-frequency distribution of liquid height and the time-frequency distribution of velocity field are obtained, and the extracted main frequency and secondary frequency data are introduced into wavelet transform to calculate the amplitude ratio of main frequency to secondary frequency, which is expressed as:

[0036] ;

[0037] in represents the nonlinear characteristics of the spectrum at time step t, and Represents the spatial average height of time step t and the spatial average velocity field at time step t The wavelet transform result at time step t is at high energy frequencies The spectrum amplitude of and Respectively and The wavelet transform results at time step t are at the main frequencies of the fluctuations Spectrum amplitude.

[0038] As a preferred solution of the single tank transportation risk early warning method based on intelligent sensors of the present invention, wherein: according to the total energy of liquid fluctuations, the time step iterative sequence data of dynamically adjusting the damping coefficient and iteratively calculating the total energy is calculated, including:

[0039] Based on the time step iteration sequence data of h and u, the total energy of liquid fluctuation is calculated and expressed as:

[0040] ;

[0041] in represents the total energy of the liquid fluctuation at time step t, p represents the liquid density, and V represents the volume of the liquid in the single tank;

[0042] Nonlinear characteristics based on the spectrum at time step t Calculating the first-order derivative to reflect the dynamic change rate of the nonlinear characteristic, and determining the weight factor based on the maximum change rate of the nonlinear characteristic;

[0043] Again based on the nonlinear characteristics of the spectrum at time step t Calculate the dynamically adjusted damping coefficient, expressed as:

[0044] ;

[0045] in represents the dynamic damping coefficient at time step t, represents the spatial average height at time step t, represents the initial damping coefficient, determined by historical data, represents the fluid viscosity factor, represents the weight factor;

[0046] Combined with the energy dissipation model, the explicit Euler method is used for discretization and iterative calculation, which can be expressed as:

[0047] ;

[0048] ;

[0049] in It represents the rate of change of the total energy of liquid fluctuation with time t, E represents the total energy, and denote the total energy of liquid fluctuations at time steps n and n+1 respectively;

[0050] Compare the calculation results of the total energy of liquid fluctuations in the current time step with that in the previous time step. When the updated time step difference no longer changes significantly during the continuous iteration process, stop the iteration and output the time step iteration sequence data of the total energy of liquid fluctuations.

[0051] As a preferred solution of the single tank transportation risk early warning method based on intelligent sensors of the present invention, the time window length is dynamically adjusted to perform dynamic risk assessment, including:

[0052] Determine the rate of change at different times based on the time-step iterative sequence data of the total energy of liquid fluctuations ;

[0053] Based on the current time step The absolute value and time window of The ratio of the maximum values ​​determines the dynamic weights of the different time change rates;

[0054] Based on the current nonlinear eigenvalue The ratio to the average value of the nonlinear eigenvalue determines the dynamic weight of the nonlinear features at different time steps;

[0055] The time window length is dynamically adjusted according to the rate of change of the total energy of the liquid fluctuation with time t, and a dynamic risk assessment is performed, which is expressed as:

[0056] ;

[0057] ;

[0058] in represents the risk assessment value at time step t, T represents the length of the dynamically adjusted time window, represents the initial energy, represents the dynamic weight of energy decay, represents the dynamic weight of nonlinear features, Indicates the maximum energy decay rate in the current window, Represents the average energy decay rate in the current window, Indicates the length of the basic time window;

[0059] The risk assessment threshold is determined based on the historical mean and standard deviation. If the risk assessment value is greater than or equal to the risk assessment threshold, the risk is judged to be high. If the risk assessment value is less than the risk assessment threshold, the risk is judged to be low.

[0060] As a preferred solution of the single tank transportation risk early warning method based on intelligent sensors of the present invention, the risk early warning includes:

[0061] Risk assessment is carried out based on the risk assessment value. When the risk is judged to be low, the normal status is displayed through a green indicator light, and a text prompt is given to the driver of the single tank transport through a visual device;

[0062] When the risk is judged to be high, real-time risk data is uploaded through the wireless network, including the risk assessment value, the total energy of the liquid fluctuation at the current time step and the rate of change of the total energy with time t, and the nonlinear characteristics of the current time step frequency;

[0063] A table is generated by a chart generation tool to provide detailed warning prompts to the tank transport driver through a visualization device.

[0064] Another object of the present invention is to provide a system for early warning of risks in single tank transportation based on intelligent sensors, which comprises:

[0065] The data acquisition and processing module collects the dynamic data of the liquid in the single tank and pre-processes the collected liquid fluctuation data;

[0066] Liquid wave simulation module, based on a two-dimensional shallow water wave model, calculates the dynamic behavior of liquid in a single tank and generates time-step iterative sequence data of liquid height and velocity fields;

[0067] The spectrum analysis module applies the Hanning window function to smooth the data, perform spectrum analysis, and calculate the spectrum amplitude and energy distribution;

[0068] The energy and damping calculation module calculates the dynamically adjusted damping coefficient according to the total energy of the liquid fluctuation and performs time-step iterative calculation of the total energy;

[0069] The risk assessment module dynamically adjusts the time window length to conduct risk assessment;

[0070] The early warning module triggers early warnings in real time based on risk assessment values ​​and thresholds.

[0071] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of the above-mentioned single tank transportation risk early warning method based on intelligent sensors when executing the computer program.

[0072] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned single tank transportation risk early warning method based on intelligent sensors.

[0073] The beneficial effects of the present invention are as follows: through the coupling of the continuity equation and the momentum equation, the height change and velocity field distribution of the liquid can be fully described, the dynamic behavior of the liquid in the single tank can be accurately reflected, the dynamic changes of the liquid height gradient and the velocity field gradient are taken into account, and the complex liquid fluctuation phenomenon can be captured. The window function is applied to weighted data to weaken the weight of the data at both ends of the time series, so that the middle part of the data contributes more significantly to the spectrum, and the two ends of the data gradually tend to zero, reducing the interference of the side lobes, and enhancing the dynamics of risk assessment. The output energy sequence can be used to judge the stability of liquid fluctuations, providing a direct basis for risk level assessment in transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0075] Figure 1 The figure is a flow chart of the risk warning method for single tank transportation based on intelligent sensors.

[0076] Figure 2 This is a schematic diagram of the structure of the single tank transportation risk warning system based on intelligent sensors. DETAILED DESCRIPTION

[0077] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0078] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0079] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0080] Example 1, reference Figure 1 , which is the first embodiment of the present invention, and provides a single tank transportation risk early warning method based on an intelligent sensor. The single tank transportation risk early warning method based on an intelligent sensor includes:

[0081] S1, collects data from the single tank for preprocessing, uses a two-dimensional shallow water wave model to calculate liquid fluctuations, and generates iterative sequence data;

[0082] Preferably, collecting data in a single tank for preprocessing includes:

[0083] Deploy built-in sensors in single tanks based on single tanks loaded on transport vehicles;

[0084] Built-in sensors include liquid level sensor, pressure sensor and acceleration sensor to collect liquid level, pressure and acceleration data in the single tank;

[0085] The sliding average method is used to eliminate high-frequency noise, smooth the level, pressure and acceleration data, and perform normalization.

[0086] By collecting liquid level, pressure and acceleration data, basic data on liquid fluctuation state and liquid level change are provided, providing rich input parameters for subsequent risk assessment models. Through preprocessing, high-frequency noise in the data is smoothed to improve the credibility and stability of the data and reduce the impact of high-frequency interference on dynamic time window adjustment and weight factor calculation.

[0087] Furthermore, a two-dimensional shallow water wave model is used to calculate the liquid wave motion and generate iterative sequence data, including:

[0088] The two-dimensional shallow water wave model is used to calculate the liquid fluctuations in the single tank, which are the continuity equation and momentum equation, expressed as:

[0089] ;

[0090] ;

[0091] in represents the instantaneous height of the liquid, represents time, u represents the two-dimensional velocity field of the liquid, g represents the gravitational acceleration, represents the gradient of liquid height, represents the gradient of the velocity field, ( represents the time rate of change of the liquid velocity, represents the divergence of the height and velocity fields);

[0092] Acquiring an initial liquid height based on a liquid level sensor and determining an initial liquid velocity field in a single tank based on a static state;

[0093] Based on the volume space within the single tank, the number of spatial grid points is determined based on historical data;

[0094] The continuity equation and momentum equation are discretized using the finite difference method FDM, expressed as:

[0095] ;

[0096] ;

[0097] ;

[0098] ;

[0099] ;

[0100] in and denote the liquid height at time step n and n+1 respectively, represents the time step, and They represent the components of the liquid velocity in the x and y directions at time step n+1, and They represent the spatial grid step size (determined by the geometric size of the single tank (e.g., if the tank length is 2 meters and the grid is divided into 20, then Δ=0.1m)), and They represent the product of the liquid height and the x-direction velocity at the grid points (i, j) and (i+1, j) in the single tank, respectively. and They represent the product of the liquid height and the y-direction velocity at the grid points (i, j) and (i, j+1) in the single tank, respectively. represents the velocity field at time step n+1;

[0101] The explicit Euler method is used for iterative calculation to update the height and velocity field, which can be expressed as:

[0102] ;

[0103] ;

[0104] Compare the height and velocity field calculation results of the current time step with those of the previous time step. When the updated time step difference no longer changes significantly during continuous iterations, stop the iteration and output the time step iteration sequence data of h and u.

[0105] Through the coupling of the continuity equation and the momentum equation, the height change and velocity field distribution of the liquid can be fully described, and the dynamic behavior of the liquid in the single tank can be accurately reflected. The dynamic changes of the liquid height gradient and the velocity field gradient are taken into account, and the complex liquid fluctuation phenomenon, including the formation and propagation of wave crests and wave troughs, can be captured. Compared with the traditional method, which relies on single-point liquid level data or static fluid models, it adapts to the dynamic characteristics of the liquid inside, and discretizes the equation based on the finite difference method (FDM). Through the time step iteration of the explicit Euler method, the liquid height and velocity field are updated through real-time iteration, and the time series data of the fluctuation can be dynamically output, providing a reliable basis for subsequent risk assessment and early warning. Through the time step iteration sequence of the liquid height and velocity field, the fluctuation intensity and frequency of the liquid in the single tank can be identified, providing data support for the adjustment of the wave-breaking board. By capturing the peak height and velocity field changes of the liquid fluctuation, it is helpful to judge the periodicity and directionality of the fluctuation, and then assist in the adjustment of the action of the wave-breaking board.

[0106] S2, applying the Hanning window function, calculating the spectrum energy distribution according to the spectrum amplitude, extracting the main frequency and secondary frequency data, and calculating the amplitude ratio of the main frequency to the secondary frequency;

[0107] Preferably, the Hanning window function is applied to calculate the spectrum energy distribution according to the spectrum amplitude, extract the main frequency and secondary frequency data, and calculate the amplitude ratio of the main frequency to the secondary frequency, including:

[0108] The spatial average value of each time step is calculated based on the time step iterative sequence data, expressed as:

[0109] ;

[0110] ;

[0111] in represents the spatial average height at time step t, represents the spatial average velocity field at time step t, and Represents the number of points of the spatial grid in the x and y directions, and represent the velocity components in the x and y directions respectively, represents the liquid height at time step t and grid point (i, j);

[0112] Applying the Hanning window function to the spatial average height and spatial average velocity field data, the spatial average height and spatial average velocity field data with high frequency noise reduced in the spectrum analysis are obtained;

[0113] The spatial average height and spatial average velocity field data are jointly fast Fourier transformed to obtain the spectrum amplitude of the height and velocity field data respectively, and the spectrum energy distribution is calculated, which is expressed as:

[0114] ;

[0115] in represents the spectral energy distribution of the kth frequency component, and represent the spectral amplitudes of the liquid height and velocity of the kth frequency component respectively;

[0116] based on Output the spectrum diagram and extract the main frequency and secondary frequency data, expressed as:

[0117] ;

[0118] ;

[0119] in represents the main frequency of fluctuation, Represents the second highest energy frequency of the fluctuation;

[0120] Make the wavelet transform act on the spatial average height simultaneously and the spatial average velocity field , the time-frequency distribution of liquid height and the time-frequency distribution of velocity field are obtained, and the extracted main frequency and secondary frequency data are introduced into wavelet transform to calculate the amplitude ratio of main frequency to secondary frequency, which is expressed as:

[0121] ;

[0122] in represents the nonlinear characteristics of the spectrum at time step t, and Respectively and The wavelet transform result at time step t is at high energy frequencies The spectrum amplitude of and Respectively and The wavelet transform results at time step t are at the main frequencies of the fluctuations Spectrum amplitude.

[0123] The spatial average height and velocity field data are smoothed by the Hanning window function, which effectively suppresses high-frequency noise, improves the accuracy of spectrum analysis results, eliminates transient high-frequency interference caused by vehicle vibration, sensor error, etc., and makes the spectrum amplitude distribution clearer. By combining fast Fourier transform, the spectrum analysis of spatial average height and velocity field data can synchronously obtain the height and velocity frequency characteristics of liquid fluctuations. The main frequency and secondary frequency data are introduced into wavelet analysis to make the time frequency distribution more accurate and capture the transient characteristics of fluctuations. In spectrum analysis, direct use of raw data will produce sidelobe effects, that is, the energy of high-frequency components leaks to the low-frequency part, affecting the spectrum accuracy. The window function is applied to weight the data to weaken the weight of the data at both ends of the time series, so that the middle part of the data contributes more significantly to the spectrum, and the two ends of the data gradually tend to zero, reducing the interference of side lobes. Based on the calculation of nonlinear characteristics, a real-time fluctuation intensity index is provided to provide a basis for dynamic time window adjustment and risk assessment threshold setting, reflecting the nonlinear intensity of liquid fluctuations and enhancing the dynamic nature of risk assessment.

[0124] S3, according to the total energy of the liquid fluctuation, calculate the time step iteration sequence data of dynamically adjusting the damping coefficient and iteratively calculating the total energy;

[0125] Preferably, according to the total energy of the liquid fluctuation, the time step iteration sequence data for calculating the dynamically adjusted damping coefficient and iteratively calculating the total energy includes,

[0126] Based on the time step iteration sequence data of h and u, the total energy of liquid fluctuation is calculated and expressed as:

[0127] ;

[0128] in represents the total energy of the liquid fluctuation at time step t, p represents the liquid density, and V represents the volume of the liquid in the single tank;

[0129] Nonlinear characteristics based on the spectrum at time step t The calculation of the first-order derivative reflects the dynamic change rate of the nonlinear characteristics, and the weight factor is determined based on the maximum change rate of the nonlinear characteristics, which is expressed as:

[0130] ;

[0131] in represents the weight factor, Indicates the dynamic change rate of nonlinear characteristics;

[0132] The dynamic viscosity value at different temperatures is obtained according to the liquid type, and the liquid shear rate is determined according to the velocity field, and the fluid viscosity factor is calculated, which is expressed as:

[0133] ;

[0134] in represents the fluid viscosity factor, represents the dynamic viscosity of the liquid at temperature R, and represent the velocity components in the x and y directions respectively;

[0135] Again based on the nonlinear characteristics of the spectrum at time step t Calculate the dynamically adjusted damping coefficient, expressed as:

[0136] ;

[0137] in represents the dynamic damping coefficient at time step t, represents the spatial average height at time step t, represents the initial damping coefficient, which is determined by historical data;

[0138] Combined with the energy dissipation model, the explicit Euler method is used for discretization and iterative calculation, which can be expressed as:

[0139] ;

[0140] ;

[0141] in It represents the rate of change of the total energy of liquid fluctuation with time t, E represents the total energy, and denote the total energy of liquid fluctuations at time steps n and n+1 respectively;

[0142] Compare the calculation results of the total energy of liquid fluctuations in the current time step with that in the previous time step. When the updated time step difference no longer changes significantly during the continuous iteration process, stop the iteration and output the time step iteration sequence data of the total energy of liquid fluctuations.

[0143] The calculation of total energy combines the liquid height and the square term of the velocity field to fully quantify the overall intensity of liquid fluctuations. The dynamic damping coefficient is adjusted and optimized to improve the adaptability of the energy dissipation model, making the iterative calculation of energy more consistent with the actual fluctuation law. The explicit Euler method is used for iterative calculation, and the time series of the total energy of liquid fluctuations is output in real time to provide dynamic input for risk assessment. The output energy series can be used to judge the stability of liquid fluctuations, providing a direct basis for risk level assessment in transportation.

[0144] S4, dynamically adjust the time window length, conduct dynamic risk assessment, and issue risk warnings;

[0145] Preferably, the time window length is dynamically adjusted to perform dynamic risk assessment, including:

[0146] Determine the rate of change at different times based on the time-step iterative sequence data of the total energy of liquid fluctuations ;

[0147] Based on the current time step The absolute value and time window of The ratio of the maximum values ​​determines the dynamic weights of the different time change rates;

[0148] Based on the current nonlinear eigenvalue The ratio to the average value of the nonlinear eigenvalue determines the dynamic weight of the nonlinear features at different time steps;

[0149] The time window length is dynamically adjusted according to the rate of change of the total energy of the liquid fluctuation with time t, and a dynamic risk assessment is performed, which is expressed as:

[0150] ;

[0151] ;

[0152] in represents the risk assessment value at time step t, T represents the length of the dynamically adjusted time window, represents the initial energy, represents the dynamic weight of energy decay, represents the dynamic weight of nonlinear features, Indicates the maximum energy decay rate in the current window, Represents the average energy decay rate in the current window, Indicates the length of the basic time window;

[0153] The risk assessment threshold is determined based on the historical mean and standard deviation. If the risk assessment value is greater than or equal to the risk assessment threshold, the risk is judged to be high. If the risk assessment value is less than the risk assessment threshold, the risk is judged to be low.

[0154] The calculation of the total energy time step change rate provides a real-time depiction of the change of liquid fluctuation intensity over time, which can capture the trend and intensity of liquid fluctuations. By analyzing the change rate of each time step, the abnormal state of liquid fluctuations (such as sudden acceleration, drastic increase in fluctuations) can be quickly discovered. The dynamic weight is based on the ratio of the absolute value of the current time step change rate to the maximum value in the time window. It can give higher weights to time periods with drastic changes, improve the sensitivity to high-risk time steps, and focus on dangerous moments when the liquid fluctuation energy changes significantly. When the liquid fluctuates violently, the time window is shortened to focus on high-risk time steps; when the fluctuation is stable, the window is extended to reduce unnecessary calculations, improve the real-time performance and computational efficiency of the model, and avoid risk assessment errors caused by fixed time windows.

[0155] Further, risk warning is carried out, including:

[0156] Risk assessment is carried out based on the risk assessment value. When the risk is judged to be low, the normal status is displayed through a green indicator light, and a text prompt is given to the driver of the single tank transport through a visual device;

[0157] When the risk is judged to be high, real-time risk data is uploaded through the wireless network, including the risk assessment value, the total energy of the liquid fluctuation at the current time step and the rate of change of the total energy with time t, and the nonlinear characteristics of the current time step frequency;

[0158] A table is generated by a chart generation tool to provide detailed warning prompts to the tank transport driver through a visualization device.

[0159] Through real-time dynamic adjustment characteristics, risk assessment can quickly adapt to the fluctuation characteristics of single tanks, provide accurate warnings for high-risk moments, and provide a graded warning mechanism (low risk, high risk) to guide operators to take corresponding measures for different risk levels, thereby reducing the probability of safety accidents such as capsizing and leakage caused by liquid fluctuations, and improving the safety of the transportation process.

[0160] Example 2, reference Figure 2 , which is the second embodiment of the present invention, and which is different from the previous embodiment, provides a system for a single tank transportation risk early warning method based on an intelligent sensor, comprising:

[0161] The data acquisition and processing module collects the dynamic data of the liquid in the single tank and pre-processes the collected liquid fluctuation data;

[0162] Liquid wave simulation module, based on a two-dimensional shallow water wave model, calculates the dynamic behavior of liquid in a single tank and generates time-step iterative sequence data of liquid height and velocity fields;

[0163] The spectrum analysis module applies the Hanning window function to smooth the data, perform spectrum analysis, and calculate the spectrum amplitude and energy distribution;

[0164] The energy and damping calculation module calculates the dynamically adjusted damping coefficient according to the total energy of the liquid fluctuation and performs time-step iterative calculation of the total energy;

[0165] The risk assessment module dynamically adjusts the time window length to conduct risk assessment;

[0166] The early warning module triggers early warnings in real time based on risk assessment values ​​and thresholds.

[0167] Example 3

[0168] This is the third embodiment of the present invention. This embodiment is different from the first two embodiments. In order to verify the beneficial effects of the method of the present invention, the specific operation process of the present invention will be demonstrated through experiments.

[0169] Simulate the parameters of a single tank. Assume that the tank is 2 meters long and the grid is divided into 4 grid points. Generate a data table based on the data collected by the sensor. The table is as follows:

[0170] Grid point (i, j) Liquid height h Velocity field in x direction Velocity field in y direction （1,1） 0.91 0.18 -0.46 （1,2） 1.05 -0.38 -0.45 （2,1） 1.08 -0.41 -0.44 （2,2） 0.93 0.29 0.28

[0171] Based on the two-dimensional shallow water wave model, the height and velocity field are updated, taking the grid point (1,1) as an example:

[0172] ;

[0173] ;

[0174] ;

[0175] ;

[0176] Generate a time step iteration sequence data table based on the data table, the table is as follows:

[0177] Grid point (i, j) Liquid height h Updated height Difference （1,1） 0.91 1.0289 0.1189 （1,2） 1.05 1.0489 -0.0011 （2,1） 1.08 1.0768 -0.0032 （2,2） 0.93 0.9285 -0.0015

[0178] Grid point (i, j) Updated x-direction velocity field Updated y-direction velocity field Difference in x direction Difference in y direction （1,1） 0.0132 -0.4415 -0.1668 0.0185 （1,2） -0.3792 -0.4412 0.0008 0.0088 （2,1） -0.4081 -0.4385 0.0019 0.0015 （2,2） 0.2879 0.2784 -0.0021 -0.0016

[0179] Based on the time step iteration sequence data table, the spatial average is calculated, including the spatial average height and the spatial average velocity field, which is expressed as:

[0180] ;

[0181] ;

[0182] Apply the Hanning window function to the spatially averaged height and velocity fields, and calculate the spectral energy distribution, as shown in the following table:

[0183] frequency Liquid height FFT amplitude Velocity field FFT amplitude Spectral energy distribution 0.0 0.5104 0.2529 0.3903 0.1 0.2552 0.1264 0.0811 0.2 0.1276 0.0632 0.203 0.3 0.0638 0.0316 0.0051

[0184] Extract the main frequency and secondary frequency, and calculate the nonlinear characteristics, which can be expressed as:

[0185] ;

[0186] Based on the volume of a single tank and the loaded liquid being water, the density of the liquid is determined as , substitute the data to calculate the total energy of liquid fluctuation, expressed as:

[0187] ;

[0188] The weight factor and fluid viscosity factor for calculating the dynamic change rate are expressed as:

[0189] ;

[0190] ;

[0191] Calculate the dynamic damping coefficient, expressed as:

[0192] ;

[0193] Further calculate the total energy of liquid fluctuations time step iteration sequence data, the table is as follows:

[0194] Time step Total energy of liquid fluctuations 0 6489.0 1 6144.009 2 5835.308 ··· ··· 10 4120.644

[0195] The dynamic time window length is calculated based on the energy time step iteration data, and dynamic risk assessment is performed, which is expressed as:

[0196] ;

[0197] ;

[0198] Determine the threshold based on historical data and conduct a dynamic risk assessment for that time step;

[0199] Compared with the traditional method which is based only on simple analysis of liquid fluctuation height or velocity field data, this method extracts the main and secondary frequencies through fast Fourier transform (FFT) and wavelet transform, and further calculates the nonlinear characteristics to capture the dynamic changes of complex fluctuation characteristics. Combined with the introduction of the influence of energy change rate and nonlinear characteristic changes into risk assessment, the time range of risk assessment can be adjusted according to the actual dynamics of liquid fluctuation, making the model more adaptable and robust.

[0200] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0201] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0202] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0203] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit with a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit with a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

Claims

1. A single tank transportation risk early warning method based on intelligent sensors, characterized by: include, Collect data from the single tank for preprocessing, use a two-dimensional shallow water wave model to calculate liquid fluctuations, and generate iterative sequence data; Apply the Hanning window function, calculate the spectrum energy distribution according to the spectrum amplitude, extract the main frequency and secondary frequency data, and calculate the amplitude ratio of the main frequency to the secondary frequency; According to the total energy of the liquid fluctuation, the time step iteration sequence data for dynamically adjusting the damping coefficient and iteratively calculating the total energy is calculated; Dynamically adjust the length of the time window, conduct dynamic risk assessment, and issue risk warnings.

2. The single tank transportation risk early warning method based on intelligent sensors according to claim 1 is characterized by: The collecting and preprocessing of the data in the single tank includes: Deploy built-in sensors in single tanks based on single tanks loaded on transport vehicles; Built-in sensors include liquid level sensor, pressure sensor and acceleration sensor to collect liquid level, pressure and acceleration data in the single tank; The sliding average method is used to eliminate high-frequency noise, smooth the level, pressure and acceleration data, and perform normalization.

3. The single tank transportation risk early warning method based on intelligent sensors according to claim 2 is characterized by: The two-dimensional shallow water wave model is used to calculate liquid fluctuations and generate iterative sequence data, including: The two-dimensional shallow water wave model is used to calculate the liquid fluctuations in the single tank, which are the continuity equation and momentum equation, expressed as: ； ； in represents the instantaneous height of the liquid, represents time, u represents the two-dimensional velocity field of the liquid, g represents the gravitational acceleration, represents the gradient of liquid height, represents the gradient of the velocity field; Acquiring an initial liquid height based on a liquid level sensor and determining an initial liquid velocity field in a single tank based on a static state; Based on the volume space within the single tank, the number of spatial grid points is determined based on historical data; The continuity equation and momentum equation are discretized using the finite difference method FDM; The explicit Euler method is used for iterative calculation to update the height and velocity field, which can be expressed as: ； ； in and denote the liquid height at time step n and n+1 respectively, represents the time step, and They represent the product of the liquid height and the x-direction velocity at the grid points (i, j) and (i+1, j) in the single tank, respectively. and They represent the product of the liquid height and the y-direction velocity at the grid points (i, j) and (i, j+1) in the single tank, respectively. represents the velocity field at time step n+1, and Respectively represent the spatial grid step size; Compare the height and velocity field calculation results of the current time step with those of the previous time step. When the updated time step difference no longer changes significantly during continuous iterations, stop the iteration and output the time step iteration sequence data of h and u.

4. The single tank transportation risk early warning method based on intelligent sensors according to claim 3 is characterized by: The method of applying the Hanning window function, calculating the spectrum energy distribution according to the spectrum amplitude, extracting the main frequency and the secondary frequency data, and calculating the amplitude ratio of the main frequency to the secondary frequency includes: Calculate the spatial average of each time step based on the time step iterative sequence data; Applying the Hanning window function to the spatial average height and spatial average velocity field data, the spatial average height and spatial average velocity field data with high frequency noise reduced in the spectrum analysis are obtained; The spatial average height and spatial average velocity field data are jointly fast Fourier transformed to obtain the spectrum amplitude of the height and velocity field data respectively, and the spectrum energy distribution is calculated, which is expressed as: ； in represents the spectral energy distribution of the kth frequency component, and represent the spectral amplitudes of the liquid height and velocity of the kth frequency component respectively; based on Output the spectrum diagram and extract the main frequency and secondary frequency data; Make the wavelet transform act on the spatial average height simultaneously and the spatial average velocity field , the time-frequency distribution of liquid height and the time-frequency distribution of velocity field are obtained, and the extracted main frequency and secondary frequency data are introduced into wavelet transform to calculate the amplitude ratio of main frequency to secondary frequency, which is expressed as: ； in represents the nonlinear characteristics of the spectrum at time step t, and Represents the spatial average height of time step t and the spatial average velocity field at time step t The wavelet transform result at time step t is at high energy frequencies The spectrum amplitude of and Respectively and The wavelet transform results at time step t are at the main frequencies of the fluctuations Spectrum amplitude.

5. The single tank transportation risk early warning method based on intelligent sensors according to claim 4 is characterized by: The time step iterative sequence data for calculating the dynamic adjustment of the damping coefficient and iteratively calculating the total energy according to the total energy of the liquid fluctuation includes: Based on the time step iteration sequence data of h and u, the total energy of liquid fluctuation is calculated and expressed as: ； in represents the total energy of the liquid fluctuation at time step t, p represents the liquid density, and V represents the volume of the liquid in the single tank; Nonlinear characteristics based on the spectrum at time step t Calculating the first-order derivative to reflect the dynamic change rate of the nonlinear characteristic, and determining the weight factor based on the maximum change rate of the nonlinear characteristic; Again based on the nonlinear characteristics of the spectrum at time step t Calculate the dynamically adjusted damping coefficient, expressed as: ； in represents the dynamic damping coefficient at time step t, represents the spatial average height at time step t, represents the initial damping coefficient, determined by historical data, represents the fluid viscosity factor, represents the weight factor; Combined with the energy dissipation model, the explicit Euler method is used for discretization and iterative calculation, which can be expressed as: ； ； in It represents the rate of change of the total energy of liquid fluctuation with time t, E represents the total energy, and denote the total energy of liquid fluctuations at time steps n and n+1 respectively; Compare the calculation results of the total energy of liquid fluctuations in the current time step with that in the previous time step. When the updated time step difference no longer changes significantly during the continuous iteration process, stop the iteration and output the time step iteration sequence data of the total energy of liquid fluctuations.

6. The method for early warning of single tank transportation risk based on intelligent sensors according to claim 5, characterized in that: The dynamically adjusting the time window length and performing dynamic risk assessment include: Determine the rate of change at different times based on the time-step iterative sequence data of the total energy of liquid fluctuations ; Based on the current time step The absolute value and time window of The ratio of the maximum values ​​determines the dynamic weights of the different time change rates; Based on the current nonlinear eigenvalue The ratio to the average value of the nonlinear eigenvalue determines the dynamic weight of the nonlinear features at different time steps; The time window length is dynamically adjusted according to the rate of change of the total energy of the liquid fluctuation with time t, and a dynamic risk assessment is performed, which is expressed as: ； ； in represents the risk assessment value at time step t, T represents the length of the dynamically adjusted time window, represents the initial energy, represents the dynamic weight of energy decay, represents the dynamic weight of nonlinear features, Indicates the maximum energy decay rate in the current window, Represents the average energy decay rate in the current window, Indicates the length of the basic time window; The risk assessment threshold is determined based on the historical mean and standard deviation. If the risk assessment value is greater than or equal to the risk assessment threshold, the risk is judged to be high. If the risk assessment value is less than the risk assessment threshold, the risk is judged to be low.

7. The single tank transportation risk early warning method based on intelligent sensors according to claim 6 is characterized by: The risk warning includes: Risk assessment is carried out based on the risk assessment value. When the risk is judged to be low, the normal status is displayed through a green indicator light, and a text prompt is given to the driver of the single tank transport through a visual device; When the risk is judged to be high, real-time risk data is uploaded through the wireless network, including the risk assessment value, the total energy of the liquid fluctuation at the current time step and the rate of change of the total energy with time t, and the nonlinear characteristics of the current time step frequency; A table is generated by a chart generation tool to provide detailed warning prompts to the tank transport driver through a visualization device.

8. A system based on the single tank transportation risk early warning method based on intelligent sensors according to any one of claims 1 to 7, characterized in that: include, The data acquisition and processing module collects the dynamic data of the liquid in the single tank and pre-processes the collected liquid fluctuation data; Liquid wave simulation module, based on a two-dimensional shallow water wave model, calculates the dynamic behavior of liquid in a single tank and generates time-step iterative sequence data of liquid height and velocity fields; The spectrum analysis module applies the Hanning window function to smooth the data, perform spectrum analysis, and calculate the spectrum amplitude and energy distribution; The energy and damping calculation module calculates the dynamically adjusted damping coefficient according to the total energy of the liquid fluctuation and performs time-step iterative calculation of the total energy; The risk assessment module dynamically adjusts the time window length to conduct risk assessment; The early warning module triggers early warnings in real time based on risk assessment values ​​and thresholds.

9. A computer device comprising: A memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the single tank transportation risk warning method based on intelligent sensors described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the single tank transportation risk early warning method based on intelligent sensors described in any one of claims 1 to 7 are implemented.

Images