Intelligent self-adaptive adjustment method for green epoxy ecological terrace based on Internet of Things

Abstract

The invention discloses an intelligent adaptive adjustment method for a green epoxy ecological terrace based on Internet of Things, and particularly relates to the field of terrace monitoring, and the method comprises the steps of S1, collection area division, S2, sensor deployment, S3, data collection, S4, data preprocessing, S5, data analysis, S6, damage judgment and S7, real-time early warning. According to the method, key and general acquisition areas are divided according to area use conditions, sensors are deployed according to different area characteristics, various data are acquired, the acquired data are processed, and feature parameters are extracted; and inputting the characteristic parameters into a mathematical model to obtain a terrace damage comprehensive evaluation index, comparing the index with a threshold value to judge whether the terrace is damaged, notifying related personnel and generating a detailed report. According to the method, real-time accurate monitoring of the state of the epoxy floor is achieved, potential damage risks can be found in advance, compared with a traditional method, the service life of the floor is effectively prolonged, the maintenance cost is reduced, and an intelligent solution is provided for management of the green epoxy ecological floor.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of floor monitoring, more specifically, the present application relates to a green epoxy ecological floor intelligent self-adaptive adjustment method based on the Internet of Things. BACKGROUND

[0002] With the rapid development of industry, epoxy floors are widely used in various places such as factories, warehouses, logistics centers, etc. Epoxy floors have many advantages such as wear resistance, pressure resistance, corrosion resistance, etc., which can effectively protect the ground base and improve the performance of the site. However, in the long-term use process, the epoxy floor is facing the challenge of complex use environment. In the area frequently subjected to heavy vehicle rolling, the floor surface is prone to wear, sanding and other problems; in the area where the equipment is parked for a long time, the local long-term pressure may cause the floor to deform and crack; and in the area where chemical substances are easily contacted, chemical corrosion will gradually damage the structure of the floor and reduce its performance.

[0003] Currently, the state monitoring of epoxy floors mainly relies on manual regular inspection, and the manual inspection method is low in efficiency and difficult to obtain the state information of the floor in real time. Moreover, the detection results are easily affected by subjective factors such as experience level difference of the detection personnel, working attitude, etc. Although some advanced monitoring methods have appeared, they have the problem of single monitoring parameter, and can only monitor a certain performance index of the floor, and cannot comprehensively evaluate the overall state of the floor. In terms of data analysis, the traditional method lacks systematicness and scientificity, and cannot accurately predict the damage trend of the floor, resulting in the inability to take effective maintenance measures in time, increasing the floor maintenance cost and downtime loss. At the same time, the traditional method does not focus on data collection, resulting in too much data and causing waste of computing power. SUMMARY

[0004] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present application provide a green epoxy ecological floor intelligent self-adaptive adjustment method based on the Internet of Things, which solves the problems in the above background art through the following scheme.

[0005] To achieve the above object, the present application provides the following technical scheme: a green epoxy ecological floor intelligent self-adaptive adjustment method based on the Internet of Things, comprising: S1: collecting area division: dividing the area frequently subjected to heavy vehicle rolling, the area where the equipment is parked for a long time and the area where chemical substances are easily contacted into key collection areas, and dividing other areas into general areas;

[0006] S2: sensor deployment: deploying different types of sensors to the data collection area according to the divided areas;

[0007] The different types of sensors include a laser roughness meter, a stylus roughness meter, an acoustic emission sensor, a microphone array, a resistance measuring instrument, a capacitance measuring instrument, and a dielectric constant tester;

[0008] S3: Internet of Things data collection: collecting surface roughness data, acoustic data, and material electrical property data according to the sensors deployed in step S2;

[0009] The surface roughness data includes arithmetic mean roughness Ra, ten-point height Rz, and root mean square roughness Rq;

[0010] The acoustic data includes sound pressure level, frequency component, and acoustic emission event count;

[0011] The material electrical property data includes resistance value, capacitance value at different frequencies, and dielectric constant;

[0012] S4: Data preprocessing: performing preprocessing and feature extraction operations on the data collected in step S3;

[0013] S5: Data analysis: inputting the parameters obtained through feature extraction into the mathematical model of the floor damage comprehensive evaluation index to obtain the floor damage comprehensive evaluation index I;

[0014] S6: Damage judgment: comparing the floor damage comprehensive evaluation index I obtained in step S5 with the set threshold T, if I >= T, it is judged that the floor has a damage risk, and if I < T, it is considered that the floor is currently in a normal state;

[0015] S7: Real-time warning: when it is detected that the floor has a damage risk, the system immediately notifies the relevant personnel through SMS, email, on-site sound and light alarm, and generates a detailed fault report including fault location, type, severity, and cause analysis.

[0016] The technical effects and advantages of the present application are as follows:

[0017] 1. The present application divides the collection area into a key collection area and a general area, increases the collection frequency of the key collection area, and reduces the collection frequency of the general area, thereby avoiding collecting too much invalid data and reducing the waste of computing power.

[0018] 2. The present application uses a variety of sensors such as a laser roughness meter, a stylus roughness meter, an acoustic emission sensor, a microphone array, a resistance measuring instrument, a capacitance measuring instrument, and a dielectric constant tester, avoids the subjective factor interference of manual detection, simultaneously obtains rich monitoring parameters, reflects the state of the floor from different angles, realizes multi-parameter comprehensive evaluation, and comprehensively and accurately masters the actual condition of the floor.

[0019] 3. By constructing a mathematical model for comprehensive floor damage assessment indicators and fitting model coefficients based on extensive historical data, this method enables in-depth analysis of data relationships and accurate calculation of comprehensive floor damage assessment indicators. Comparing this indicator with a threshold value not only determines the current condition of the floor but also effectively predicts the direction of floor damage based on the changing trends of various characteristic parameters. This provides a scientific basis for pre-emptive maintenance planning, shifting from reactive maintenance to proactive prevention, and reducing repair costs and downtime losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a schematic diagram of the overall structure of the present invention;

[0021] Figure 2 This is a schematic diagram of the device connection of the present invention. DETAILED DESCRIPTION

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0023] As attached Figure 1 The method is a green epoxy ecological floor intelligent adaptive adjustment method based on the Internet of Things, including a data acquisition terminal, a data analysis terminal, an early warning module and a data center;

[0024] The data acquisition terminal includes a laser roughness meter, a stylus roughness meter, an acoustic emission sensor, a microphone array, a resistance meter, a capacitance meter, and a dielectric constant tester, which are respectively responsible for collecting different types of data. The laser roughness meter is used to collect surface roughness data, the acoustic emission sensor is responsible for collecting acoustic emission event counts in acoustic data, and the resistance meter is used to collect resistance values ​​in material electrical property data. These sensors are installed at corresponding positions on the floor according to regional characteristics, and the collected data are transmitted to the data analysis terminal in real time or periodically. The specific equipment models are not specifically limited in this embodiment;

[0025] The data analysis terminal receives data transmitted by the data acquisition terminal through a data interface, pre-processes the data using algorithms such as mean filtering and linear interpolation in the software, and then uses a specific algorithm to calculate characteristic values ​​such as the surface roughness change rate and the sound pressure level change slope, and calculates the damage assessment index based on the characteristic values;

[0026] The early warning module receives feature data of the data analysis terminal and evaluation result data of the dynamic model construction module through the communication interface, judges whether the floor is damaged, and when judging that the floor has a damage risk, sends early warning information through the sound and light alarm device, the display screen and the mobile phone APP, clearly shows the damage type and position, and gives repair suggestions;

[0027] The data center connects the data collection terminal, the data analysis terminal and the early warning module through a network, receives data and information sent by each module in real time, realizes centralized monitoring and management of the whole system, and management personnel can check the real-time state, historical data and early warning information of the floor in the data center, make decisions according to the situation, and issue control instructions;

[0028] The connection relationship between the above-mentioned data collection terminal, data analysis terminal, early warning module and data center can be seen from Figure 2

[0029] The specific implementation of the application includes the following steps:

[0030] S1: Collecting area division: the area frequently subjected to heavy vehicle rolling, the area where equipment is parked for a long time and the area easily contacting chemical substances are divided into key collecting areas, and other areas are divided into general areas;

[0031] It should be further explained that the key collecting area increases the sensor deployment density and improves the data collection frequency, and the general area deploys sensors and collects data according to the conventional density;

[0032] S2: Sensor deployment: different types of sensors are deployed to the data collection area according to the divided area;

[0033] The different types of sensors include a laser roughness meter, a stylus roughness meter, an acoustic emission sensor, a microphone array, a resistance measuring instrument, a capacitance measuring instrument and a dielectric constant tester;

[0034] It should be further explained that the sensor deployment method is as follows:

[0035] For the general area, a movable laser roughness meter is installed every 50-100 square meters. These devices can move on the preset path through the track or automatic navigation system to scan and measure the floor surface; in the key collecting area, such as the contact part of the floor and the equipment, the frequently passing channel intersection and the like, the stylus roughness meter is fixedly installed, and one measuring point is arranged every 10-20 square meters, and the measuring data is transmitted to the data analysis terminal in real time through the data line;

[0036] ​In the expansion joint of the key collection area, the edge of the large equipment foundation and the weak structure area, an acoustic emission sensor is pasted every 5-10 meters; the sensor is tightly connected with the floor surface through special coupling agent, to ensure that it can effectively receive the acoustic emission signals generated by internal stress changes; in the general area, multiple microphone arrays are arranged, each microphone array is composed of 4-8 microphones, arranged in a circular or square shape, the array spacing is 10-20 meters, and the collected sound signals are transmitted to the data analysis terminal through wireless mode;

[0037] For the general area, fix the electrodes of the resistance measuring instrument on the floor surface in a group of 50-100 square meters, and the key collection area is 10-25 square meters. A measuring instrument using four-probe method is used to ensure good contact between the probe and the floor material, and is connected to the data acquisition equipment through wires. The resistance value is measured regularly. For the general area, set a measuring point every 100-200 square meters, and the key collection area is 50-100 square meters. Install a capacitance measuring instrument and a dielectric constant tester. The capacitance measuring instrument is connected to the floor material through an alternating current signal source. The dielectric constant tester uses the principle of parallel plate capacitor to place the test plate on the floor surface. The capacitance value and dielectric constant are measured automatically at a set time interval, and the data is transmitted to the data analysis terminal.

[0038] S3: Internet of Things data collection: collect surface roughness data, acoustic data and material electrical property data according to the sensors deployed in step S2;

[0039] The surface roughness data includes arithmetic average roughness Ra, ten-point height Rz and root mean square roughness Rq;

[0040] The acoustic data includes sound pressure level, frequency component and acoustic emission event count;

[0041] The material electrical property data includes resistance value, capacitance value at different frequencies and dielectric constant;

[0042] It needs to be further explained that the collection method of surface roughness data, acoustic data and material electrical property data is as follows:

[0043] The laser roughness meter moves at a speed of 1-5 meters per second along a preset path to continuously scan the floor surface, and data is recorded every 10-20 square centimeters. The stylus roughness meter automatically measures at fixed measurement points every 1-2 hours, each measurement lasting 1-2 minutes to obtain surface roughness data for a measurement point. The acoustic emission sensor monitors acoustic emission signals generated by changes in internal stress of the floor in real time, with a data acquisition frequency of 1000-10000 times per second to capture minor acoustic changes. The microphone array collects sound signals every 5-10 seconds, each collection lasting 1-2 seconds, and the collected sound signals are digitally processed. The resistance meter measures resistance value once a day, applies a constant current during measurement, and the duration is 5-10 seconds. The voltage value is recorded and the resistance is calculated. The capacitance measuring instrument and the dielectric constant tester measure once a week. The capacitance measuring instrument measures capacitance value at 1 kHz, 10 kHz and 100 kHz. The dielectric constant tester calculates the dielectric constant according to the measured capacitance value combined with the electrode parameters;

[0044] S4: data preprocessing: preprocessing and feature extraction operations are performed on the data collected in step S3;

[0045] Specifically, the preprocessing operation is as follows: mean filtering is used to smooth the data and remove random noise. Linear interpolation method is used to fill in missing values by linear estimation according to the values of the previous and subsequent time. Values exceeding the range of mean value plus or minus 3 times standard deviation are regarded as abnormal values and deleted. Finally, the data is normalized.

[0046] The feature extraction operation includes:

[0047] Ra change rate calculation: let Ra i be the arithmetic mean roughness value at the i-th time point, and the time interval be Δt. For example, if data is collected every 1 day, then Δt = 1, and the change rate R Ra of Ra in the time period [i, i+n] is calculated as follows:

[0048]

[0049] It should be further pointed out that this change rate reflects the change speed of the average degree of micro-unevenness of the floor surface in a certain time period. For example, if R Ra is positive and large, it indicates that the floor surface roughness shows an upward trend in this time period, and there may be a situation of accelerated wear.

[0050] Rz change rate calculation: for ten-point height Rz, let Rz i be the value at the i-th time point, and the change rate R Rz in the time period [i, i+n] is calculated as follows:

[0051]

[0052] It should be further explained that the Rz change rate can reflect the change of the surface large fluctuation characteristics. If R Rz The significant change may mean that the floor surface appears more obvious pit or convex change.

[0053] Rq change rate calculation: for the root mean square roughness Rq, set Rq i The change rate R Rq The calculation formula is:

[0054]

[0055] It should be further explained that the Rq change rate reflects the change rate of the real situation of the surface roughness from the statistical point of view, which helps to more comprehensively understand the dynamic change of the floor surface micro morphology.

[0056] Sound pressure level change with time slope calculation: take time t as the horizontal coordinate, sound pressure level L p As the vertical coordinate, draw the sound pressure level change curve with time, and observe the curve dL p / dt to describe the change trend. For example, if the curve shows an upward trend, it can be represented as dL p / dt>0, and the greater the upward slope, the faster the sound pressure level increases with time; if the curve shows a downward trend, dL p / dt<0;

[0057] Frequency component distribution characteristics calculation: Fourier transform the collected acoustic data to convert the time domain signal into the frequency domain signal, set X(f) as the frequency domain signal, f as the frequency, and the frequency component distribution characteristics can be described by calculating the signal energy proportion in different frequency intervals, for example, in the frequency interval [f1,f2], the signal energy accounts for the proportion P [f1,f2] The calculation formula is:

[0058] Where f max is the highest frequency that can be detected by the acoustic data acquisition device;

[0059] It should be further explained that by analyzing the change of the energy proportion in different frequency intervals, the change of the sound source can be judged. For example, the increase of the high frequency energy proportion may be related to the material micro fracture and other faults.

[0060] Acoustic emission event count growth rate calculation: set N iAcoustic emission event count at the ith time point, time interval Δt, growth rate R of acoustic emission event count in the time period [i, i+n] N The calculation formula is:

[0061]

[0062] It should be further explained that the growth rate of acoustic emission event count reflects the change of acoustic emission event frequency. If R N increases, it may indicate that the internal defects of the floor are developing, such as the expansion of cracks or the generation of new cracks.

[0063] Resistance value change slope calculation: let R i be the resistance value at the ith time point, time interval Δt, and the change slope S R of the resistance value in the time period [i, i+n] The calculation formula is:

[0064]

[0065] It should be further explained that the change slope of the resistance value can reflect the change speed of the current resistance ability of the floor material. When S R changes greatly, it may indicate that the internal structure of the floor material has changed due to reasons such as moisture, aging or chemical corrosion.

[0066] Capacitance value change slope calculation: for capacitance value C, let C i be the value at the ith time point, time interval Δt, and the change slope S C of the capacitance value in the time period [i, i+n] The calculation formula is:

[0067]

[0068] It should be further explained that the change slope of the capacitance value reflects the change of the material's charge storage ability. For example, if S C is positive and gradually increases, it may mean that the dielectric properties of the floor material have changed, which may be related to moisture or internal structure changes of the material.

[0069] Dielectric constant change slope: let ∈ i be the dielectric constant at the ith time point, time interval Δt, and the change slope S ∈ of the dielectric constant in the time period [i, i+n] The calculation formula is:

[0070]

[0071] It should be further explained that the change slope of the dielectric constant can be used to evaluate the changes of the molecular structure and polarization characteristics in the floor material. When S ∈When the normal fluctuation range is exceeded, it may indicate that the performance of the floor material is abnormal, thereby affecting the overall performance of the floor.

[0072] S5: Data analysis: input the parameters obtained by feature extraction into the mathematical model of the floor damage comprehensive evaluation index to obtain the floor damage comprehensive evaluation index I;

[0073] Specifically, the mathematical model of the floor damage comprehensive evaluation index is as follows:

[0074]

[0075] wherein R Ra , R Rz , and R Rq are the change rates of the arithmetic average roughness, ten-point height, and root mean square roughness in the surface roughness data, dL p / dt is the change rate of the sound pressure level with time, P [f1,f2] is the proportion of signal energy in the frequency interval [f1, f2] to the total energy, R N is the acoustic emission event count growth rate, S R , S C , and S ∈ are the change slopes of the resistance value, capacitance value, and dielectric constant, respectively, and α1, α2, α3, β1, β2, β3, γ1, γ2, γ3, δ1, δ2, δ3, and θ are model coefficients, and α1+α2+α3+β1+β2+β3+γ1+γ2+γ3+δ1+δ2+δ3+θ=1, which are determined by historical data fitting or experiments. These coefficients reflect the relative importance and influence degree of different parameters on floor damage evaluation.

[0076] S6: Damage judgment: compare the floor damage comprehensive evaluation index I obtained in step S5 with the set threshold T, if I≥T, it is judged that the floor has a damage risk, and if I

[0077] It should be specifically noted that if I≥T, it is judged that the floor has a damage risk, at this time, each data feature can be further analyzed, such as observing whether R Ra exceeds the normal range more, to judge whether the damage is caused by surface wear; or checking the value of dL p / dt to analyze whether there is an acoustic anomaly caused by internal structural problems, so as to determine the possible damage type and location, and if I

[0078] It should be further noted that the threshold T is obtained by analyzing a large amount of historical data and actual engineering experience.

[0079] S7: Real-time early warning: when detecting that the floor exists damage risk, the system immediately informs the relevant personnel through SMS, email, on-site sound and light alarm, and generates a detailed fault report, including fault location, type, severity and cause analysis.

[0080] Secondly: the drawings in the disclosed embodiments of the application only involve the structures involved in the disclosed embodiments, other structures can refer to the usual design, and in the case of no conflict, the same embodiment and different embodiments of the application can be combined with each other;

[0081] Finally: the above only describes the preferred embodiments of the application and is not used to limit the application, and any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the application shall be included in the protection scope of the application.

Claims

1. A green epoxy ecological floor intelligent adaptive adjustment method based on the Internet of Things, characterized in that: Including: S1: Collection area division: Divide the areas frequently subjected to heavy vehicle rolling, areas where equipment is parked for a long time, and areas prone to contact with chemical substances into key collection areas, and other areas into general areas; S2: Sensor deployment: Deploy different types of sensors to the data collection areas according to the divided areas; The different types of sensors include laser roughness meters, stylus roughness meters, acoustic emission sensors, microphone arrays, resistance measuring instruments, capacitance measuring instruments, and dielectric constant testers; S3: Internet of Things data collection: Collect surface roughness data, acoustic data, and material electrical property data according to the sensors deployed in step S2; The surface roughness data includes arithmetic mean roughness Ra, ten-point height Rz, and root mean square roughness Rq; The acoustic data includes sound pressure level, frequency components, and acoustic emission event counts; The material electrical property data includes resistance values, capacitance values at different frequencies, and dielectric constants; S4: Data preprocessing: Perform preprocessing and feature extraction operations on the data collected in step S3; S5: Data analysis: Input the parameters obtained by feature extraction into the mathematical model of the comprehensive evaluation index of floor damage to obtain the comprehensive evaluation index I of floor damage; S6: Damage judgment: Compare the comprehensive evaluation index I of floor damage obtained in step S5 with the set threshold T. If I≥T, it is judged that there is a risk of floor damage. If I<T, it is considered that the floor is currently in a normal state; S7: Real-time warning: When it is detected that there is a risk of floor damage, the system immediately notifies relevant personnel via text messages, emails, on-site sound and light alarms, and generates a detailed fault report, including the fault location, type, severity, and cause analysis.

2. The method for intelligent adaptive adjustment of green epoxy ecological flooring based on the Internet of Things according to claim 1 is characterized in that: The sensor deployment method is as follows: For general areas, install a movable laser roughness meter every 50 - 100 square meters. These devices can move on a preset path through a track or an automatic navigation system to scan and measure the floor surface. In key collection areas, fixedly install stylus roughness meters, set a measurement point every 10 - 20 square meters, and transmit the measurement data to the data analysis terminal in real time through a data cable; In the expansion joints, edges of large equipment foundations, and structurally weak areas of key collection areas, paste an acoustic emission sensor every 5 - 10 meters. The sensor is tightly connected to the floor surface through a special coupling agent to ensure effective reception of acoustic emission signals generated by internal stress changes. In general areas, arrange multiple microphone arrays. Each microphone array consists of 4 - 8 microphones and is arranged in a circular or square shape with an array spacing of 10 - 20 meters. Transmit the collected sound signals to the data analysis terminal wirelessly; For general areas, the electrodes of the resistance meter are fixed on the floor surface in a group of 50-100 square meters. The key collection area is 10-25 square meters. A four-probe method measuring instrument is used to ensure that the probes are in good contact with the floor material. They are connected to the data acquisition equipment through wires to measure the resistance value regularly. For general areas, a measurement point is set up every 100-200 square meters. The key collection area is 50-100 square meters. A capacitance meter and a dielectric constant tester are installed. The capacitance meter is connected to the floor material through an AC signal source. The dielectric constant tester uses the principle of parallel plate capacitors to place the test plates on the floor surface. The capacitance value and dielectric constant are automatically measured at set time intervals, and the data is transmitted to the data analysis terminal.

3. The method for intelligent adaptive adjustment of green epoxy ecological flooring based on the Internet of Things according to claim 1 is characterized in that: The method for collecting surface roughness data, acoustic data, and material electrical characteristic data is as follows: The laser roughness meter moves along a preset path at a speed of 1-5 meters per second, continuously scanning the floor surface and recording data every 10-20 square centimeters scanned. The stylus roughness meter automatically performs a measurement at a fixed measuring point every 1-2 hours, with each measurement lasting 1-2 minutes to obtain surface roughness data for a measuring point. The acoustic emission sensor monitors the acoustic emission signals generated by changes in internal stress of the floor in real time. The data acquisition frequency is set to 1000-10000 times per second to capture tiny acoustic changes. The microphone array collects sound signals every 5-10 seconds, each acquisition lasting 1-2 seconds, and the collected sound signals are digitized. The resistance meter measures the resistance value once a day, applying a constant current for 5-10 seconds, recording the voltage value and calculating the resistance. The capacitance meter and dielectric constant tester perform measurements once a week. The capacitance meter measures the capacitance value at 1kHz, 10kHz, and 100kHz, and the dielectric constant tester calculates the dielectric constant based on the measured capacitance value combined with the plate parameters.

4. The method for intelligent adaptive adjustment of green epoxy ecological flooring based on the Internet of Things according to claim 1 is characterized in that: The preprocessing operation is as follows: use mean filtering to smooth the data to remove random noise, use linear interpolation to perform linear estimation to fill missing values ​​based on the values ​​of the previous and next moments, and delete data values ​​that exceed the mean plus or minus 3 times the standard deviation as outliers, and finally normalize the data.

5. The method for intelligent adaptive adjustment of green epoxy ecological flooring based on the Internet of Things according to claim 1 is characterized in that: The feature extraction operation includes: Calculation of Ra change rate: Assume Ra i is the arithmetic mean roughness value at the i-th time point, and the time interval is Δt. For example, if data is collected every day, then Δt = 1, and the rate of change of Ra in the time period [i, i + n] is R Ra The calculation formula is: Rz change rate calculation: For the ten-point height Rz, let Rz i is the value at the i-th time point, and its rate of change R in the time period [i,i+n] Rz The calculation formula is: Calculation of Rq change rate: For the root mean square roughness Rq, let Rq i is the value at the i-th time point, and its rate of change R in the time period [i,i+n] Rq The calculation formula is: Calculation of the slope of sound pressure level over time: With time t as the horizontal axis, the sound pressure level L p As the vertical axis, draw the curve of sound pressure level changing with time, and observe the trend of the curve dL p / dt to describe the trend of change; Calculation of frequency component distribution characteristics: Perform Fourier transform on the collected acoustic data to convert the time domain signal into a frequency domain signal. Let X(f) be the frequency domain signal and f be the frequency. The distribution characteristics of the frequency component can be described by calculating the proportion of signal energy in different frequency intervals. For example, in the frequency interval [f1, f2], the proportion of signal energy to total energy P [f1,f2] The calculation formula is: Among them, f max The highest frequency that can be detected by the acoustic data acquisition equipment; Calculation of acoustic emission event count growth rate: Assume N i is the acoustic emission event count at the i-th time point, the time interval is Δt, and the growth rate R of the acoustic emission event count in the time period [i, i+n] N The calculation formula is: Resistance value change slope calculation: Let R i is the resistance value at the i-th time point, the time interval is Δt, and the slope of the resistance change in the time period [i, i+n] is S R The calculation formula is: Calculation of capacitance change slope: For capacitance C, let C i is the value at the i-th time point, the time interval is Δt, and the slope of the change of the capacitance value in the time period [i, i+n] is S C The calculation formula is: Dielectric constant change slope: Let ∈ i is the dielectric constant at the i-th time point, the time interval is Δt, and the slope of the dielectric constant change in the time period [i, i+n] is S ∈ The calculation formula is:

6. The method for intelligent adaptive adjustment of green epoxy ecological flooring based on the Internet of Things according to claim 1 is characterized in that: The mathematical model of the comprehensive evaluation index of floor damage is as follows: where R Ra 、R Rz 、R Rq are the change rates of arithmetic mean roughness, ten-point height, and root mean square roughness in the surface roughness data, dL p / dt is the rate of change of sound pressure level with time, P [f1,f2] is the ratio of signal energy in the frequency interval [f1, f2] to the total energy, R N is the acoustic emission event count growth rate, S R 、S C 、S ∈ where α1, α2, α3, β1, β2, β3, γ1, γ2, γ3, δ1, δ2, δ3 and θ are the model coefficients, and α1+α2+α3+β1+β2+β3+γ1+γ2+γ3+δ1+δ2+δ3+θ=1.

Images