Wireless intelligent material moisture detection method and device

Abstract

The invention discloses a wireless intelligent material moisture detection method and device, and relates to the technical field of material moisture detection.The wireless intelligent material moisture detection method comprises the steps that tobacco in a tobacco box is pre-detected through ultrasonic waves to obtain tobacco density distribution, and a detection path is generated according to the tobacco density distribution; label data on the tobacco box are obtained, batch data of tobacco are obtained according to the label data, detection calibration parameters are generated, and detection equipment conducts detection calibration according to the detection calibration parameters; the detection equipment is inserted into the tobacco box, a detection needle head of the detection equipment releases the movable end head, and moisture distribution data of tobacco in the tobacco box is obtained; according to the detection equipment, temperature and humidity data and gas data in the tobacco box are obtained, a compression data chain is generated in combination with the moisture distribution data, and the compression data chain is sent to the cloud; and the cloud performs multi-dimensional fusion prediction to generate a comprehensive quality report of the tobacco. The method has the effect of improving the efficiency and accuracy of detecting the moisture in the tobacco.

Description

Technical Field

[0001] This application relates to the technical field of material moisture detection, and particularly to a wireless intelligent material moisture detection method and device. Background Art

[0002] Tobacco is a herbaceous plant that can be processed into cigarettes for sale, and is a raw material with high economic value and great importance. During the acquisition and processing of tobacco, it is necessary to control the moisture content in tobacco. On the one hand, it is to ensure that the tobacco will not rot or be damaged during storage, and on the other hand, it is to improve the subsequent processing quality.

[0003] In the prior art, when detecting the moisture in tobacco, generally the detection device is inserted into a tobacco box or a tobacco bag, and then the moisture content in tobacco is detected by means of infrared absorption, time-domain frequency-domain reflection, etc. The above methods are all sampling detections of tobacco. However, during the detection process, there will be uneven tobacco density, resulting in different local detection results, making the final result inaccurate. At the same time, during the detection process, only the moisture content in tobacco is referred to, while ignoring the influence of other factors on the detection process and results. In addition, the dielectric properties of different batches of tobacco are different, and the method of manually calibrating the equipment before each detection is time-consuming, laborious and inefficient. Summary of the Invention

[0004] The purpose of the present invention is to provide a wireless intelligent material moisture detection method and device to solve the problems raised in the above background art.

[0005] In a first aspect, this application provides a wireless intelligent material moisture detection method, and the method includes: Using ultrasonic waves to pre-detect the tobacco in a tobacco box to obtain ultrasonic data of the tobacco, obtaining the tobacco density distribution in the tobacco box according to the ultrasonic data, and generating a detection path according to the tobacco density distribution; Obtaining label data on the tobacco box, obtaining batch data of the tobacco according to the label data, generating detection calibration parameters according to the batch data, and sending the detection calibration parameters to a detection device, and the detection device performs detection calibration according to the detection calibration parameters; Inserting the detection device into the tobacco box, the detection needle of the detection device releases a mobile head, and the mobile head moves and detects according to the detection path to obtain moisture distribution data of the tobacco in the tobacco box; According to the detection device, obtaining temperature and humidity data and gas data in the tobacco box, combining the moisture distribution data, the temperature and humidity data, and the gas data to perform preprocessing to generate a compressed data chain, and sending the compressed data chain to the cloud; The cloud performs multi-dimensional fusion prediction on the tobacco in the tobacco box according to the compressed data chain, generates a predicted deterioration risk of the tobacco, and generates a comprehensive quality report of the tobacco according to the predicted deterioration risk.

[0006] Preferably, the steps of pre-detecting the tobacco in the tobacco box using ultrasonic waves to obtain ultrasonic data of the tobacco, obtaining the tobacco density distribution in the tobacco box according to the ultrasonic data, and generating a detection path according to the tobacco density distribution are as follows: Arrange an ultrasonic transmitting / receiving array around the tobacco box, transmit ultrasonic waves to the tobacco in the tobacco box for pre-detection, and obtain ultrasonic data of the tobacco; Perform noise reduction and filtering on the ultrasonic data, and perform time-domain compensation on the ultrasonic data after noise reduction and filtering to obtain target ultrasonic data; Extract the sound wave velocity, attenuation amount, and scattering intensity in the target ultrasonic data, and perform inversion according to the sound wave velocity, the attenuation amount, and the scattering intensity to obtain the tobacco density distribution in the tobacco box; According to the tobacco density distribution, divide the space of the tobacco box to obtain a plurality of tobacco blocks, and mark the density value of each tobacco block; Pre-select two tobacco blocks as initial blocks, and select the tobacco block that is connected to the initial block and has the closest density value as the target block; Obtain the distance value between the two target blocks, and determine whether the distance value exceeds a preset distance threshold. If it is determined that the distance value exceeds the distance threshold, re-select the target block; Based on the target block, repeat the selection to generate a detection path.

[0007] Preferably, the steps of generating detection calibration parameters according to the batch data and sending the detection calibration parameters to the detection device, and the detection device performing detection calibration according to the detection calibration parameters are as follows; Obtain historical detection data and historical batch data, and generate a historical batch correspondence table by corresponding the historical detection data and the historical batch data one by one; According to the historical batch correspondence table, extract the historical batch characteristics of the tobacco in the historical detection data corresponding to each batch; According to the multiple historical batch characteristics, obtain the detection parameters for each historical batch characteristic; Based on each of the detection parameters, generate a calibration parameter set, and select detection calibration parameters from the calibration parameter set according to the batch data; Send the detection calibration parameters to the detection device, and the detection device performs self-detection calibration according to the detection calibration parameters.

[0008] Preferably, the step of inserting the detection device into the tobacco box, releasing the mobile tips of the detection needles of the detection device, and moving and detecting according to the detection path to obtain the moisture distribution data of the tobacco in the tobacco box is specifically as follows: Insert the detection device into the tobacco box, and extract the needle spatial positions of the two detection needles of the detection device in the tobacco box; Based on the needle spatial positions and the plurality of tobacco cubes, obtain the starting tobacco cube, correct the detection path according to the starting tobacco cube, and generate a target detection path; Based on the target detection path, the two detection needles each release a mobile tip, and the two mobile tips move in the tobacco box according to the target detection path, and collect the capacitance change data in the tobacco box in real time and upload it to the detection device; Correspond the capacitance change data with the tobacco cubes to obtain local moisture data, and integrate the plurality of local moisture data to obtain the moisture distribution data of the tobacco in the tobacco box.

[0009] Preferably, before the step of the two detection needles each releasing a mobile tip based on the target detection path, it further includes: A temperature probe is arranged between the two detection needles, and the length of the temperature probe is longer than that of the two detection needles; After the detection device is inserted into the tobacco box, the temperature probe collects the temperature data in the tobacco box, and compares the temperature data with the preset standard temperature data to obtain a temperature difference; Based on the temperature difference, the temperature probe performs a heating or cooling operation to make the two detection needles in a standard temperature environment; The two detection needles perform a calibration detection in the standard temperature environment to obtain starting detection data, and generate a detection compensation parameter that changes with temperature according to the starting detection data.

[0010] Preferably, the step of the two mobile tips moving in the tobacco box according to the target detection path and collecting the capacitance change data in the tobacco box in real time is specifically as follows: The two mobile tips move in the tobacco box according to the target detection path, and collect the temperature and humidity data, pressure data, and initial capacitance change data in real time during the movement; Extract the temperature and humidity timestamps, pressure timestamps, and capacitance timestamps in the temperature and humidity data, the pressure data, and the initial capacitance change data respectively; Align the temperature and humidity timestamp, the pressure timestamp, and the capacitance timestamp, and concatenate the temperature and humidity data, the pressure data, and the initial capacitance change data after timestamp alignment to generate concatenated capacitance change data; Add the detection compensation parameters to the concatenated capacitance change data and then perform internal data fusion to generate capacitance change data.

[0011] Preferably, the step of combining the moisture distribution data, the temperature and humidity data, and the gas data for preprocessing to generate a compressed data chain and sending the compressed data chain to the cloud is specifically as follows: Extract the moisture key data, the temperature and humidity key data, and the gas key data from the moisture distribution data, the temperature and humidity data, and the gas data to generate a key data set; Generate a key data histogram based on the key data set, set an alarm red line on the key data histogram, and detect whether there are data bars reaching or exceeding the alarm red line; If it is detected that there is a data bar exceeding the alarm red line, extract the data type of the data bar, and generate a corresponding alarm reminder according to the data type and send it to the detection device for alarm; Compress the key data set to generate a data header, integrate the moisture distribution data, the temperature and humidity data, and the gas data and generate a compressed feature vector; Assemble the data header and the compressed feature vector to generate a compressed data chain, and send the compressed data chain to the cloud.

[0012] Preferably, the step of the cloud performing multi-dimensional fusion prediction on the tobacco in the tobacco box according to the compressed data chain to generate a predicted deterioration risk of the tobacco and generating a comprehensive quality report of the tobacco according to the predicted deterioration risk is specifically as follows: The cloud performs data expansion and restoration on the compressed data chain to obtain a complete detection data set; According to the gas data in the detection data set, obtain the air composition data and the air chemistry data in the tobacco box; Generate a deterioration risk value of the tobacco in the tobacco box according to the air composition data and the air chemistry data in the detection data set; According to the temperature and humidity data in the detection data set, obtain a deterioration promotion value of the temperature and humidity in the current tobacco box on the deterioration of the tobacco; Predict the deterioration distribution map of the tobacco in the current tobacco box according to the moisture distribution data in the detection data set; Generate a predicted spoilage risk for the tobacco by combining the spoilage distribution map, the spoilage risk value, and the spoilage promotion value, and generate a comprehensive quality report for the tobacco based on the predicted spoilage risk.

[0013] In a second aspect, the present application provides a wireless intelligent material moisture detection device, which includes: A pre-detection module: used to pre-detect the tobacco in the tobacco box using ultrasonic waves to obtain ultrasonic data of the tobacco, obtain the tobacco density distribution in the tobacco box according to the ultrasonic data, and generate a detection path according to the tobacco density distribution; An OTA calibration module: used to obtain the label data on the tobacco box, obtain the batch data of the tobacco according to the label data, generate detection calibration parameters according to the batch data, and send the detection calibration parameters to the detection device, and the detection device performs detection calibration according to the detection calibration parameters; A moisture detection module: used to insert the detection device into the tobacco box, the detection needle of the detection device releases a mobile end head, and the mobile end head moves and detects according to the detection path to obtain the moisture distribution data of the tobacco in the tobacco box; A data preprocessing module: used to obtain the temperature, humidity data, and gas data in the tobacco box according to the detection device, preprocess and generate a compressed data chain by combining the moisture distribution data, the temperature, humidity data, and the gas data, and send the compressed data chain to the cloud; A risk prediction module: used for the cloud to perform multi-dimensional fusion prediction on the tobacco in the tobacco box according to the compressed data chain, generate a predicted spoilage risk for the tobacco, and generate a comprehensive quality report for the tobacco according to the predicted spoilage risk.

[0014] In summary, the present application includes at least one of the following beneficial technical effects: Pre - detect the tobacco box through ultrasonic waves to obtain the tobacco density distribution in the tobacco box, and then generate a detection path according to this density distribution. Then, obtain batch data based on the label data on the tobacco box. Acquire historical detection data and historical batch data, obtain the historical batch characteristics during the detection of each batch in history, generate detection parameters according to the historical batch characteristics, then generate detection calibration parameters according to the detection parameters, and remotely calibrate the detection device according to the detection calibration parameters. Then insert the detection device into the tobacco box. The detection device includes two detection needles and a temperature probe. There is a movable detection tip at the top of each of the two detection needles. After the detection device is inserted, the temperature probe identifies the current temperature and then adjusts the temperature. The movable tips do not move for the time being. Then, conduct an initial detection in a standard temperature environment, and generate detection compensation parameters at the same time. Subsequently, adjust the detection path according to the spatial position of the movable tips to obtain the target detection path, and then conduct a mobile detection. At the same time, use the detection compensation parameters to compensate and correct the detection results to obtain the moisture distribution data. Subsequently, collect the temperature, humidity and gas data in the tobacco box, pre - process and compress these data and send them to the cloud. The cloud predicts the deterioration situation of the tobacco based on the received data and generates a comprehensive quality report. This improves the efficiency and accuracy of moisture detection in tobacco. Description of the Drawings

[0015] Figure 1 is a flowchart of the steps of a wireless intelligent material moisture detection method provided by an embodiment of the present application; Figure 2 is a block diagram of the modules of a wireless intelligent material moisture detection device provided by an embodiment of the present application.

[0016] Explanation of the reference numerals in the drawings: 1. Pre - detection module; 2. OTA calibration module; 3. Moisture detection module; 4. Data pre - processing module; 5. Risk prediction module. Detailed Embodiment

[0017] The following is combined with Figure 1 - Figure 2 to further elaborate on the present application in detail, but the embodiments of the present invention are not limited thereto.

[0018] The embodiments of the application disclose a wireless intelligent material moisture detection method and device.

[0019] In this embodiment, a wireless intelligent material moisture detection method includes: S100: Pre - detect the tobacco in the tobacco box using ultrasonic waves to obtain the ultrasonic data of the tobacco, obtain the tobacco density distribution in the tobacco box according to the ultrasonic data, and generate a detection path according to the tobacco density distribution; S200: Obtain the label data on the tobacco box, get the batch data of the tobacco according to the label data, generate detection and calibration parameters based on the batch data, and send the detection and calibration parameters to the detection device. The detection device performs detection and calibration according to the detection and calibration parameters; S300: Insert the detection device into the tobacco box. The detection needle of the detection device releases the mobile head, and the mobile head moves and detects according to the detection path to obtain the moisture distribution data of the tobacco in the tobacco box; S400: According to the detection device, obtain the temperature, humidity data and gas data in the tobacco box, preprocess and generate a compressed data chain by combining the moisture distribution data, temperature, humidity data and gas data, and send the compressed data chain to the cloud; S500: The cloud performs multi-dimensional fusion prediction on the tobacco in the tobacco box according to the compressed data chain, generates the predicted deterioration risk of the tobacco, and generates a comprehensive quality report of the tobacco according to the predicted deterioration risk.

[0020] It should be noted that the above modules are only the basic steps of this embodiment. In the specific implementation process, on the premise of not affecting the overall implementation effect, some steps can be appropriately added, reduced or modified.

[0021] The steps of using ultrasonic waves to pre-detect the tobacco in the tobacco box to obtain the ultrasonic data of the tobacco, obtaining the tobacco density distribution in the tobacco box according to the ultrasonic data, and generating the detection path according to the tobacco density distribution are specifically as follows: Arrange an ultrasonic transmitting / receiving array around the tobacco box, emit ultrasonic waves to the tobacco in the tobacco box for pre-detection, and obtain the ultrasonic data of the tobacco; Perform noise reduction and filtering on the ultrasonic data, and perform time-domain compensation on the noise-reduced and filtered ultrasonic data to obtain the target ultrasonic data; Extract the sound wave velocity, attenuation amount and scattering intensity in the target ultrasonic data, and perform inversion according to the sound wave velocity, attenuation amount and scattering intensity to obtain the tobacco density distribution in the tobacco box; According to the tobacco density distribution, divide the tobacco box into multiple tobacco cubes in space, and mark the density value of each tobacco cube; Pre-select two tobacco cubes as the initial cubes, and select the tobacco cube that is connected to the initial cube and has the closest density value as the target cube; Obtain the distance value between the two target cubes, judge whether the distance value exceeds the preset distance threshold. If it is judged that the distance value exceeds the distance threshold, re-select the target cube; Based on the target cubes, repeat the selection to generate the detection path.

[0022] In operation, taking the tobacco boxes of batch A in a certain tobacco warehouse in 2023 as an example, 8 groups of ultrasonic transmitting / receiving arrays are arranged around the box body, and ultrasonic waves with a frequency of 1 MHz are used for scanning to obtain the original ultrasonic data containing 1,200 groups of echo signals. After wavelet noise reduction and Butterworth filtering of the original data, the 5 μs signal delay caused by the wooden board material of the box body is eliminated through the time-domain compensation algorithm to obtain the target ultrasonic data. The extracted compensated sound wave velocity is 1,520 m / s (the normal value for tobacco should be 1,480 - 1,500 m / s), the attenuation coefficient reaches 3.2 dB / cm (the normal value is 2.5 dB / cm), and the scattering intensity distribution shows the characteristics of high on the east side (0.45) and low on the west side (0.32). According to the acoustic inversion model, a tobacco density distribution map is reconstructed. The box body with dimensions of 1.2 m × 0.8 m × 0.6 m is divided into 480 tobacco cubes of 10 cm³, and the marked density value range is 380 - 420 kg / m³ (the normal density is 400 ± 15 kg / m³). Two initial cubes D12 and D35 (density 402 kg / m³) are preselected. Adjacent cubes with a density difference less than 5 kg / m³ are connected through the neighborhood search algorithm. When it is detected that the distance between D12 and E12 exceeds 15 cm, a threshold alarm is triggered, and cube E15 (density 398 kg / m³) is reselected to construct the path. Finally, an S-shaped detection path containing 68 connection nodes is generated, covering 85% of the box body area.

[0023] Steps for generating detection calibration parameters according to batch data and sending the detection calibration parameters to the detection device for the detection device to perform detection calibration according to the detection calibration parameters are as follows: Obtain historical detection data and historical batch data, and generate a historical batch correspondence table by corresponding the historical detection data and historical batch data one by one; According to the historical batch correspondence table, extract the historical batch characteristics of tobacco in the historical detection data corresponding to each batch; Based on multiple historical batch characteristics, obtain the detection parameters for each historical batch characteristic; Based on each detection parameter, generate a calibration parameter set, and select detection calibration parameters from the calibration parameter set according to the batch data; Send the detection calibration parameters to the detection device, and the detection device performs self-detection calibration according to the detection calibration parameters.

[0024] In operation, taking the tobacco boxes of batch A in a certain tobacco warehouse in 2023 as an example, the labels of the tobacco boxes of batch A show a production date of May 12, 2023, and a standard moisture content value of 12.5%. The system retrieves historical data for the past 3 months to construct a batch correspondence table and finds that the tobacco of batch 202303 shows an abnormal dielectric constant (ε = 28.5, normal ε = 32 ± 1.5) due to different raw material origins, and generates targeted calibration parameters: adjusting the capacitance detection reference value from 120 pF to 115 pF and increasing the signal amplification gain by 8%. After the calibration parameters are wirelessly transmitted to the detection device, the device automatically corrects the bias voltage in the detection circuit, reducing the zero drift from ±0.3 pF to ±0.1 pF. The system also loads the moisture-capacitance curve equation unique to this batch: C = 0.85W² + 12.3W + 98.6 (W is the moisture percentage), replacing the standard equation C = 0.78W² + 11.5W + 102.4.

[0025] The steps of inserting the detection device into the tobacco box, where the detection needles of the detection device release the mobile heads, and the mobile heads move and detect according to the detection path to obtain the moisture distribution data of the tobacco in the tobacco box are specifically as follows: Insert the detection device into the tobacco box and extract the needle spatial positions of the two detection needles of the detection device in the tobacco box; Based on the needle spatial positions and multiple tobacco cubes, obtain the starting tobacco cube, and correct the detection path according to the starting tobacco cube to generate a target detection path; Based on the target detection path, the two detection needles each release a mobile head, and the two mobile heads move in the tobacco box according to the target detection path and collect the capacitance change data in the tobacco box in real time, and upload it to the detection device; Correspond the capacitance change data with the tobacco cubes to obtain local moisture data, and integrate multiple local moisture data to obtain the moisture distribution data of the tobacco in the tobacco box.

[0026] In operation, taking the tobacco boxes of batch A in a certain tobacco warehouse in 2023 as an example, after the detection device is inserted into the box at a 45-degree angle, the two needles are respectively positioned at the three-dimensional coordinates (0.2, 0.3, 0.15) m and (0.5, 0.3, 0.15) m. The path planning module optimizes the detection path into a spiral propulsion type in combination with the initial position, increasing the number of nodes from 68 to 75, and the coverage rate reaches 92%. The mobile head moves along the path at a speed of 5 mm / s and collects data every 0.5 seconds. A sudden change in the capacitance value is detected in tobacco cube No. 3 (coordinates 0.3, 0.4, 0.2), jumping from the reference value of 115 pF to 138 pF (corresponding to a moisture content of 16.7%), generating local abnormal data. A total of 1500 groups of capacitance data are obtained for the entire path, and the moisture distribution map generated after spatial interpolation processing shows that there is a high-humidity area with a diameter of 25 cm and a moisture content of 18.5% in the northeast corner of the box.

[0027] Before the steps of the two detection needles each releasing the mobile needle tip based on the target detection path, it further includes: A temperature probe is provided between the two detection needles, and the length of the temperature probe is longer than that of the two detection needles; After the detection device is inserted into the tobacco box, the temperature probe collects the temperature data in the tobacco box, and compares the temperature data with the preset standard temperature data to obtain a temperature difference; Based on the temperature difference, the temperature probe performs heating or cooling operations to make the two detection needles in a standard temperature environment; The two detection needles perform calibration detection in a standard temperature environment to obtain initial detection data, and generate detection compensation parameters that vary with temperature according to the initial detection data.

[0028] In operation, taking the tobacco boxes of batch A in 2023 in a certain tobacco warehouse as an example, there is also a temperature probe set during the detection. The temperature probe with a length of 15 cm measures the temperature inside the box as 22 °C (standard 25 °C), triggering the heating device to work for 3 minutes to raise the needle environment to 25 ± 0.5 °C. The calibration detection shows that the reference capacitance value changes from 115 pF at room temperature to 117 pF, and the temperature compensation coefficient K = 0.15 pF / °C is established. When the temperature fluctuates to 24.3 °C during subsequent mobile detection, compensation is automatically applied to the collected 125 pF data: 125 + (25 - 24.3) * 0.15 = 125.105 pF. This compensation mechanism reduces the moisture detection error from ±0.8% to ±0.3%.

[0029] The steps of the two mobile needle tips moving in the tobacco box according to the target detection path and collecting the capacitance change data in the tobacco box in real time are specifically as follows: The two mobile needle tips move in the tobacco box according to the target detection path, and collect temperature and humidity data, pressure data, and initial capacitance change data in real time during the movement; Extract the temperature and humidity timestamps, pressure timestamps, and capacitance timestamps in the temperature and humidity data, pressure data, and initial capacitance change data respectively; Align the temperature and humidity timestamps, pressure timestamps, and capacitance timestamps, and concatenate the temperature and humidity data, pressure data, and initial capacitance change data after timestamp alignment to generate concatenated capacitance change data; Add the detection compensation parameters to the concatenated capacitance change data and then perform internal data fusion to generate capacitance change data.

[0030] In operation, taking the tobacco boxes of batch A in a certain tobacco warehouse in 2023 as an example, the mobile head synchronously collected a temperature of 24.8°C, a pressure of 32.6 kPa, and an original capacitance of 128 pF at path node 47 (coordinates 0.6, 0.5, 0.3). The temperature and humidity data (timestamp 2023-07-12T14:23:45.200) with an interval of 0.2 seconds and the capacitance data (timestamp 2023-07-12T14:23:45.205) were linearly interpolated and aligned through the timestamp alignment module. The compensated capacitance data of 129.2 pF and the pressure data were used to construct a feature vector [129.2, 32.6, 24.8]. After PCA dimensionality reduction, a fused capacitance value of 130.5 pF (corresponding to a moisture content of 15.2%) was generated. The variance of the data at this node decreased from 2.3 in separate detections to 0.7 after fusion.

[0031] The steps of preprocessing the moisture distribution data, temperature and humidity data, and gas data to generate a compressed data chain and sending the compressed data chain to the cloud are as follows: Extract the moisture key data, temperature and humidity key data, and gas key data from the moisture distribution data, temperature and humidity data, and gas data to generate a key data set; Generate a key data histogram based on the key data set, set an alarm red line on the key data histogram, and detect whether there are data bars that reach or exceed the alarm red line; If it is detected that there are data bars exceeding the alarm red line, extract the data types of the data bars, and generate corresponding alarm reminders according to the data types and send them to the detection devices for alarm; Compress the key data set to generate a data header, and integrate the moisture distribution data, temperature and humidity data, and gas data to generate a compressed feature vector; Assemble the data header and the compressed feature vector to generate a compressed data chain, and send the compressed data chain to the cloud.

[0032] In operation, taking the tobacco boxes of batch A in a certain tobacco warehouse in 2023 as an example, the key values are extracted from the moisture data: the highest is 18.5%, the lowest is 12.1%, and the variance is 2.3. The temperature and humidity key data: the average temperature is 24.5°C (standard deviation 0.8), and the relative humidity is 72%. The CO2 concentration in the gas data reaches 2300 ppm (threshold 2000 ppm). The constructed histogram shows that the CO2 column exceeds the red alarm line by 15%, triggering a warning signal. Huffman coding is used for data compression. The original 2.1 MB data is compressed into a 356 KB data chain, including a 128-byte data header (recording the key value range) and a feature vector matrix. The compression ratio reaches 6:1, and the wireless transmission time is shortened from 58 seconds to 9 seconds.

[0033] The steps for the cloud to perform multi-dimensional fusion prediction on the tobacco in the tobacco box according to the compressed data chain, generate the predicted deterioration risk of the tobacco, and generate a comprehensive quality report of the tobacco are as follows: The cloud performs data expansion and restoration on the compressed data chain to obtain a complete detection data set; According to the gas data in the detection data set, obtain the air component data and air chemistry data in the tobacco box; Generate a deterioration risk value of the tobacco in the tobacco box according to the air component data and air chemistry data in the detection data set; According to the temperature and humidity data in the detection data set, obtain the deterioration promotion value of the current temperature and humidity in the tobacco box on the deterioration of the tobacco; According to the moisture distribution data in the detection data set, predict the deterioration distribution map of the tobacco in the current tobacco box; Combine the deterioration distribution map, the deterioration risk value, and the deterioration promotion value to generate the predicted deterioration risk of the tobacco, and generate a comprehensive quality report of the tobacco according to the predicted deterioration risk.

[0034] In application, taking the tobacco box of batch A in a certain tobacco warehouse in 2023 as an example, after the cloud restores the data, it is identified that the CO2 exceeds the standard and the acetaldehyde content is 0.15 ppm (the safety value < 0.1 ppm), and the calculated deterioration risk index reaches 78 points (the threshold is 60). The deterioration promotion factor is calculated as 1.25 based on the temperature and humidity data (formula: e^(0.05*(T - 20)+0.03*(H - 65))). The moisture distribution prediction model shows that the probability of expansion in the high humidity area (>16%) reaches 85% within 48 hours. A comprehensive evaluation generates a quality report: the current safety level is B, it is recommended to implement dehumidification treatment within 24 hours, the estimated treatment cost is 320 RMB, and the deterioration risk can be reduced to 32 points. The report is stored on the blockchain and synchronized to the warehouse management system.

[0035] The embodiment of the present invention provides a wireless intelligent material moisture detection device, which uses a wireless intelligent material moisture detection method as described in any one of the above, and the device includes the following: Pre-detection module 1: used to pre-detect the tobacco in the tobacco box using ultrasonic waves to obtain the ultrasonic data of the tobacco, obtain the tobacco density distribution in the tobacco box according to the ultrasonic data, and generate a detection path according to the tobacco density distribution; OTA calibration module 2: used to obtain the label data on the tobacco box, obtain the batch data of the tobacco according to the label data, generate detection calibration parameters according to the batch data, and send the detection calibration parameters to the detection device, and the detection device performs detection calibration according to the detection calibration parameters; Moisture detection module 3: It is used to insert the detection device into the tobacco box. The detection needle of the detection device releases the mobile tip, and the mobile tip moves and detects according to the detection path to obtain the moisture distribution data of the tobacco in the tobacco box; Data preprocessing module 4: It is used to obtain the temperature, humidity data and gas data in the tobacco box according to the detection device, preprocess and generate a compressed data chain by combining the moisture distribution data, temperature, humidity data and gas data, and send the compressed data chain to the cloud; Risk prediction module 5: It is used for the cloud to perform multi-dimensional fusion prediction on the tobacco in the tobacco box according to the compressed data chain, generate the predicted deterioration risk of the tobacco, and generate a comprehensive quality report of the tobacco according to the predicted deterioration risk.

[0036] The above are all the preferred embodiments of this application. The protection scope of this application is not limited accordingly. Therefore, all equivalent changes made according to the structure, shape and principle of this application should be covered within the protection scope of this application.

Claims

1. A wireless intelligent material moisture detection method, characterized in that: The following steps are involved: Using ultrasound to pre-detect tobacco in a tobacco box to obtain ultrasonic data of the tobacco, obtaining a density distribution of tobacco in the tobacco box according to the ultrasonic data, and generating a detection path according to the density distribution of tobacco; Acquire label data on a tobacco box, obtain batch data of the tobacco according to the label data, generate detection calibration parameters according to the batch data, and send the detection calibration parameters to a detection device, and the detection device performs detection calibration according to the detection calibration parameters; Inserting the detection device into a tobacco box, the detection needle of the detection device releases the moving end head, and the moving end head performs moving detection according to the detection path to obtain the moisture distribution data of the tobacco in the tobacco box; According to the detection device, the temperature and humidity data and the gas data in the tobacco box are obtained, the moisture distribution data, the temperature and humidity data and the gas data are pre-processed to generate a compressed data chain, and the compressed data chain is sent to the cloud; The cloud performs a multi-dimensional fusion prediction on the tobacco in the tobacco box according to the compressed data link, generates a predicted deterioration risk of the tobacco, and generates a comprehensive quality report of the tobacco according to the predicted deterioration risk.

2. A wireless intelligent material moisture detection method according to claim 1, characterized in that: The steps of using ultrasound to pre-detect tobacco in a tobacco box to obtain ultrasonic data of the tobacco, obtaining tobacco density distribution in the tobacco box according to the ultrasonic data, and generating a detection path according to the tobacco density distribution are specifically as follows: An ultrasonic transmitting / receiving array is arranged around the tobacco box to transmit ultrasonic waves to the tobacco in the tobacco box for pre-detection to obtain ultrasonic wave data of the tobacco; Denoising and filtering the ultrasonic data, and performing time domain compensation on the denoised and filtered ultrasonic data to obtain target ultrasonic data; Extracting the sound wave velocity, attenuation and scattering intensity from the target ultrasonic data, and inverting the sound wave velocity, the attenuation and the scattering intensity to obtain the tobacco density distribution in the tobacco box; According to the tobacco density distribution, the tobacco box is spatially divided to obtain a plurality of tobacco blocks, and the density value of each tobacco block is marked; Preselecting two tobacco blocks as initial blocks, and selecting the tobacco block connected to the initial blocks and having the closest density value as the target block; Obtaining a distance value between the two target blocks, determining whether the distance value exceeds a preset distance threshold, and if it is determined that the distance value exceeds the distance threshold, reselecting a target block; Based on the target block, selection is repeated to generate a detection path.

3. A wireless intelligent material moisture detection method according to claim 2, characterized in that: Generating detection calibration parameters according to the batch data, and sending the detection calibration parameters to the detection device, the detection device performs detection calibration according to the detection calibration parameters, specifically; Acquire historical test data and historical batch data, and generate a historical batch correspondence table by making a one-to-one correspondence between the historical test data and the historical batch data; Extracting historical batch characteristics of tobacco from the historical test data corresponding to each batch according to the historical batch correspondence table; According to the plurality of historical batch characteristics, obtaining a detection parameter specific to each of the historical batch characteristics; Based on each of the detection parameters, a calibration parameter set is generated, and detection calibration parameters are selected from the calibration parameter set according to the batch data; The detection calibration parameters are sent to the detection device, and the detection device performs self-detection calibration according to the detection calibration parameters.

4. A wireless intelligent material moisture detection method according to claim 3, characterized in that: The detection device is inserted into a tobacco box, the detection needle of the detection device releases the moving end head, and the moving end head performs moving detection according to the detection path to obtain the moisture distribution data of the tobacco in the tobacco box, specifically, the steps are: Inserting the detection device into a tobacco box, and extracting the needle space positions of two detection needles of the detection device in the tobacco box; Based on the needle space position and the plurality of tobacco blocks, a starting tobacco block is obtained, and the detection path is corrected according to the starting tobacco block to generate a target detection path; Based on the target detection path, the two detection needles release their respective mobile terminals, and the two mobile terminals move in the tobacco box according to the target detection path, and collect data on capacitance changes in the tobacco box in real time, and upload the data to the detection device; The capacitance change data is matched with the tobacco block to obtain local moisture data, and a plurality of the local moisture data are integrated to obtain moisture distribution data of the tobacco in the tobacco box.

5. A wireless intelligent material moisture detection method according to claim 4, characterized in that: Based on the target detection path, before the step of the two detection needles respectively releasing the moving end heads, the method further includes: A temperature probe is arranged between the two detection needles, and the temperature probe is longer than the two detection needles; When the detection device is inserted into the tobacco box, the temperature probe collects temperature data in the tobacco box and compares the temperature data with preset standard temperature data to obtain a temperature difference; Based on the temperature difference, the temperature probe performs a heating or cooling operation to place the two detection needles in a standard temperature environment; The two detection needles are subjected to calibration detection in the standard temperature environment to obtain initial detection data, and detection compensation parameters that vary with temperature are generated according to the initial detection data.

6. A wireless intelligent material moisture detection method according to claim 5, characterized in that: The two mobile terminals move in the tobacco box according to the target detection path and collect the data of capacitance change in the tobacco box in real time, specifically: The two mobile terminals move in the tobacco box according to the target detection path, and collect temperature and humidity data, pressure data and initial capacitance change data in real time during the movement; Respectively extracting the temperature and humidity timestamps, the pressure timestamps, and the capacitance timestamps from the temperature and humidity data, the pressure data, and the initial capacitance change data; Aligning the temperature and humidity timestamp, the pressure timestamp, and the capacitance timestamp, and connecting the temperature and humidity data, the pressure data, and the initial capacitance change data after the timestamp alignment in series to generate series capacitance change data; After the detection compensation parameter is added to the series capacitance change data, internal data fusion is performed to generate capacitance change data.

7. A wireless intelligent material moisture detection method according to claim 6, characterized in that: The steps of preprocessing the moisture distribution data, the temperature and humidity data, and the gas data to generate a compressed data chain, and sending the compressed data chain to the cloud are specifically as follows: Extracting moisture key data, temperature and humidity key data, and gas key data from the moisture distribution data, the temperature and humidity data, and the gas data to generate a key data set; Generate a key data bar graph based on the key data set, set an alarm red line on the key data bar graph, and detect whether there is a data column that reaches or exceeds the alarm red line; If it is detected that the data column exceeds the alarm red line, the data type of the data column is extracted, and a corresponding alarm reminder is generated according to the data type and sent to the detection device for alarm; Compressing the key data set to generate a data header, integrating the moisture distribution data, the temperature and humidity data, and the gas data to generate a compressed feature vector; The data header and the compressed feature vector are assembled to generate a compressed data chain, and the compressed data chain is sent to the cloud.

8. A wireless intelligent material moisture detection method according to claim 7, characterized in that: The cloud performs multi-dimensional fusion prediction on the tobacco in the tobacco box according to the compressed data link to generate a predicted deterioration risk of the tobacco, and generates a comprehensive quality report of the tobacco according to the predicted deterioration risk, specifically: The cloud performs data expansion and restoration on the compressed data chain to obtain a complete detection data set; Obtaining air composition data and air chemistry data in the tobacco box according to the gas data in the detection data set; Generate a risk value of deterioration of tobacco in a tobacco box according to the air composition data and the air chemistry data in the detection data set; According to the temperature and humidity data in the detection data set, a deterioration promotion value of the temperature and humidity in the current tobacco box on tobacco deterioration is obtained; Predicting a deterioration distribution map of tobacco in a current tobacco box according to the moisture distribution data in the detection data set; The predicted deterioration risk of tobacco is generated by combining the deterioration distribution map, the deterioration risk value and the deterioration promotion value, and a comprehensive quality report of tobacco is generated based on the predicted deterioration risk.

9. A wireless intelligent material moisture detection device, the system using a wireless intelligent material moisture detection method as claimed in any one of claims 1 to 8, characterized in that: The system comprises: Pre-detection module: used for pre-detecting tobacco in the tobacco box using ultrasound to obtain ultrasonic data of the tobacco, obtaining tobacco density distribution in the tobacco box according to the ultrasonic data, and generating a detection path according to the tobacco density distribution; OTA calibration module: used to obtain label data on a tobacco box, obtain batch data of tobacco according to the label data, generate detection calibration parameters according to the batch data, and send the detection calibration parameters to the detection device, and the detection device performs detection calibration according to the detection calibration parameters; Moisture detection module: used to insert the detection device into the tobacco box, the detection needle of the detection device releases the moving end head, and the moving end head performs moving detection according to the detection path to obtain the moisture distribution data of the tobacco in the tobacco box; Data preprocessing module: used to obtain temperature and humidity data and gas data in the tobacco box according to the detection device, preprocess the moisture distribution data, the temperature and humidity data and the gas data to generate a compressed data chain, and send the compressed data chain to the cloud; Risk prediction module: used for the cloud to perform multi-dimensional fusion prediction on the tobacco in the tobacco box according to the compressed data link, generate a predicted deterioration risk of the tobacco, and generate a comprehensive quality report of the tobacco according to the predicted deterioration risk.

Images