A granary grain storage anomaly monitoring method, system, device and medium

Abstract

The present application relates to the technical field of grain storage monitoring, in particular to a kind of granary grain storage abnormal monitoring method, system, equipment and medium, method includes: obtaining the collection data of multidimensional sensor in granary, extracts the drift characteristic value of each sensor collection data current period;The absolute value of the drift characteristic value of each sensor collection data current period is compared with pre-set threshold value, establishes and includes abnormal sensor and the sensor group associated with abnormal sensor;Obtain the collection data or drift characteristic value of each type sensor in the same period in the sensor group, fuse multi-sensor data and carry out correlation analysis, distinguish environmental interference or real grain storage anomaly;According to the abnormal type of real grain storage anomaly, trigger hierarchical response.Determine abnormal sensor by comparing the absolute value of drift characteristic value, establish the sensor group associated therewith, consider the relevance of different abnormal types and other factors, it is helpful to more accurately carry out abnormal analysis.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of grain storage monitoring, in particular to a grain storage abnormality monitoring method, system, device and medium. BACKGROUND

[0002] Grain storage management has high requirements on the environment, and grain temperature is one of the important indicators for ensuring the safe storage of grain. Only by timely and accurately measuring the grain temperature data of each layer of the grain pile and analyzing the environment according to the detected temperature and humidity data, can the loss caused by mold, unbalanced temperature and humidity, etc. during storage be avoided.

[0003] The existing grain storage environment monitoring system vertically inserts a temperature and humidity detector into the grain pile, and sets a temperature and humidity alarm value. When the temperature or humidity exceeds the threshold value, an alarm will be triggered. However, the placement positions of the temperature and humidity detectors are mostly spaced apart, and each temperature and humidity detector can only monitor the grain pile within the effective radius around it. The heat transfer of the grain pile is relatively slow, and the monitoring data of each sensor is detected and analyzed in isolation, lacking correlation between multiple monitoring data. Moreover, a single sensor is subject to environmental interference and sensor drift, and cannot effectively distinguish between real grain storage abnormalities and temporary environmental interference. The single threshold value detection and alarm has a high false alarm rate. SUMMARY

[0004] To solve the above problems, the present application provides a grain storage abnormality monitoring method in the first aspect, comprising:

[0005] Obtaining the collection data of the multi-dimensional sensors in the grain storage, performing residual calculation on the data sequence of each sensor, and extracting the drift feature value of the current period of the collection data of each sensor;

[0006] Comparing the absolute value of the drift feature value of the current period of the collection data of each sensor with the preset threshold value through the preset threshold value, and determining the sensor equal to or greater than the threshold value; taking the sensor as an abnormal sensor, and establishing a sensor group containing the abnormal sensor and the sensors associated with the abnormal sensor;

[0007] Based on the sensor group of the abnormal sensor, obtaining the collection data or drift feature value of each type of sensor in the same period in the sensor group, performing correlation analysis on the multi-sensor data, and distinguishing between environmental interference and real grain storage abnormalities;

[0008] Triggering a hierarchical response according to the abnormal type of the real grain storage abnormality.

[0009] The residual calculation on the data sequence of each sensor and the extraction of the drift feature value of the current period of the collection data of each sensor are specifically as follows:

[0010] According to the reference value corresponding to the sensor, the residual value is obtained by subtracting the reference value from the collected data of the sensor in the current period;

[0011] The residual mean and the residual standard deviation are calculated by obtaining the residual value of the same type of sensor in the current period respectively, and the residual value is standardized based on the residual mean and the residual standard deviation;

[0012] The residual value of the sensor in each period is linearly fitted, and the slope value is obtained, which is the drift characteristic value of the sensor in the current period.

[0013] The formula for standardizing the residual value is:

[0014]

[0015] In the formula, R t The residual value of the sensor in the current period is represented by R t std The residual value of the sensor in the current period is represented by R μ R The residual mean of the same type of sensor is represented by R σ R The residual standard value of the same type of sensor is represented by R

[0016] The establishment of the sensor group containing the abnormal sensor and the sensor associated with the abnormal sensor includes:

[0017] If the abnormal sensor is a temperature detection sensor, the temperature detection sensor is taken as the center, the distance between the temperature detection sensor and the temperature detection sensor closest to the right side is taken as the radius, and all temperature detection sensors in the circle are taken as sensor group one.

[0018] If the abnormal sensor is a humidity detection sensor, the humidity detection sensor, the temperature detection sensor and the gas detection sensor are taken as sensor group two.

[0019] If the abnormal sensor is a vibration detection sensor, the vibration detection sensor, the insect monitoring instrument and the infrared monitoring camera are taken as sensor group three.

[0020] If the abnormal sensor is an insect monitoring instrument, the insect monitoring instrument, the temperature detection sensor and the humidity detection sensor are taken as sensor group four.

[0021] The fusion of multi-sensor data for correlation analysis to distinguish environmental interference or real grain storage anomaly is:

[0022] When the abnormal sensor is a temperature detection sensor, the drift characteristic values of each temperature detection sensor in the same period in the sensor group one are obtained, and the drift characteristic values are compared with a temperature drift threshold value, if the absolute values of the drift characteristic values of two or more temperature detection sensors are greater than the temperature drift threshold value, it is a real grain storage abnormality, that is, the temperature imbalance in the grain depot; if only the absolute value of the drift characteristic value of the abnormal sensor is greater than the temperature drift threshold value, it is an environmental interference;

[0023] When the abnormal sensor is a humidity detection sensor, if the humidity detection value of the humidity detection sensor decreases and the temperature detection value of the temperature detection sensor increases, the relative humidity decreases, and the humidity detection sensor signal is distorted, if the current time is in summer, it is a real grain storage abnormality;

[0024] If the humidity detection value of the humidity detection sensor increases, the temperature detection value of the temperature detection sensor increases, and the CO2 detection concentration of the gas detection sensor increases and the O2 detection concentration decreases, it is a real grain storage abnormality.

[0025] The correlation analysis of the fusion multi-sensor data further includes:

[0026] When the abnormal sensor is a vibration detection sensor, if the vibration detection value of the vibration detection sensor increases, the pest detection density of the pest monitoring instrument increases or the image recognition of the infrared monitoring camera is abnormal, it is a real grain storage abnormality, that is, there is a pest infestation; if only the absolute value of the drift characteristic value of the abnormal sensor is greater than the vibration drift threshold value, it is an environmental interference;

[0027] If the abnormal sensor is a pest monitoring instrument, if the pest detection density of the pest monitoring instrument increases, and the temperature detection value of the temperature detection sensor increases and the humidity detection value of the humidity detection sensor increases, it is a real grain storage abnormality; if only the absolute value of the drift characteristic value of the abnormal sensor is greater than the density drift threshold value, it is an environmental interference.

[0028] The hierarchical response is triggered according to the type of the real grain storage abnormality, and the specific operation is:

[0029] If there is only one real grain storage abnormality, a three-level response is triggered;

[0030] If there are two real grain storage abnormalities or the three-level response lasts for a long time without being eliminated, a two-level response is triggered;

[0031] If there are two or more real grain storage abnormalities, a one-level response is triggered.

[0032] The second aspect of the present application provides a grain depot grain storage abnormality monitoring system, comprising:

[0033] The feature extraction module is configured to acquire collection data of multi-dimensional sensors in the grain depot, perform residual error calculation on data sequences of the sensors, and extract drift feature values of the collection data of the sensors in a current period;

[0034] The comparison module is configured to compare absolute values of the drift feature values of the collection data of the sensors in the current period with a preset threshold value through the preset threshold value, determine sensors equal to or greater than the threshold value, take the sensors as abnormal sensors, and establish a sensor group containing the abnormal sensors and sensors associated with the abnormal sensors;

[0035] The analysis processing module is configured to acquire collection data or drift feature values of sensors of different types in the same period in the sensor group based on the abnormal sensors, perform correlation analysis on the multi-sensor data, and distinguish between environmental interference and real grain storage abnormality.

[0036] The abnormal response module is configured to trigger a hierarchical response according to the abnormal type of the real grain storage abnormality.

[0037] The third aspect provides a grain depot grain storage abnormality monitoring device, including a processor and a memory, wherein the processor implements a grain depot grain storage abnormality monitoring method as described above when executing a computer program saved in the memory.

[0038] A computer readable storage medium for storing a computer program, wherein the computer program is executed by a processor to implement a grain depot grain storage abnormality monitoring method as described above.

[0039] Beneficial effects: The present application is a kind of grain depot grain storage abnormality monitoring method, by residual error calculation on each sensor data sequence, and further extract drift feature value, can accurately capture the trend of data change with time, can effectively exclude interference, highlight the abnormal change characteristics of data, provide reliable basis for subsequent abnormal judgment;

[0040] At the same time, by comparing the absolute values of the drift feature values to determine the abnormal sensors, establishing a sensor group associated with the abnormal sensors, considering the correlation of different abnormal types and other factors, it is helpful to more accurately analyze the abnormality; acquiring collection data or drift feature values of sensors of different types in the same period in the group for correlation analysis can effectively distinguish between environmental interference and real grain storage abnormality, and greatly improve the accuracy of abnormal judgment. BRIEF DESCRIPTION OF DRAWINGS

[0041] The scheme and advantages of the present application will become clear to those skilled in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not considered as limiting the present application.

[0042] In the drawings:

[0043] Figure 1 A flowchart of a grain storage abnormality monitoring method. DETAILED DESCRIPTION

[0044] Exemplary embodiments of the present disclosure will be described in greater detail below with reference to the accompanying drawings.

[0045] The present embodiment provides a grain storage abnormality monitoring method, which is applied to a grain storage environment monitoring system. The grain storage environment monitoring system includes temperature detection sensors, humidity detection sensors, gas detection sensors, vibration detection sensors, insect situation monitoring instruments, and infrared monitoring cameras. The number of each sensor is set according to the environment of the grain storage to be measured. The grain storage environment monitoring system is deployed in the grain storage and connected to an Internet of Things management platform. The environment detection data in the grain storage is transmitted to the Internet of Things management platform through the Internet of Things technology, which facilitates remote operation and adjustment of abnormal environments.

[0046] Grain storage needs to monitor environmental information in real time to prevent the stored grain in the grain storage from having unbalanced temperature and humidity, mold, and insect infestation. Therefore, in addition to opening the grain storage opening during grain transportation, the grain storage environment information may change. When the grain transportation is completed and the grain is stored statically, the grain storage is in a closed state. Ideally, each grain storage needs to maintain a low-temperature and low-oxygen environment suitable for storing corresponding grain according to the type of stored grain. The detection data of each sensor at different time periods has less difference, but the actual situation is much more complex.

[0047] In order to realize long-term effective preservation of grain storage in the grain storage and timely identification and monitoring of abnormal problems of the grain storage, referring to Figure 1 , the grain storage abnormality monitoring method specifically implements the following steps:

[0048] S1, acquiring the collection data of the multi-dimensional sensors in the grain storage, performing residual error calculation on the data sequence of each sensor, and extracting the drift characteristic value of the collection data of each sensor at the current time period;

[0049] Taking the collection data of any temperature detection sensor as an example, the data sequence of the temperature detection sensor is subjected to residual error calculation, and the drift characteristic value of the collection data of the temperature detection sensor at the current time period is extracted. The operation is specifically as follows:

[0050] According to the environmental reference benchmark value corresponding to the sensor, the residual error value is obtained by subtracting the collection data of the sensor at the current time period from the environmental reference benchmark value;

[0051] The residual error values of the same type of sensors at the current time period are acquired respectively, and the residual error mean and the residual error standard deviation are calculated. The residual error values are standardized based on the residual error mean and the residual error standard deviation, and the formula is as follows:

[0052]

[0053] In the formula, R t R represents the residual value of the current period of the sensor; R t std R represents the residual value of the current period of the sensor; R μ R R represents the residual mean value of the same type of sensor; R σ R R represents the residual mean value of the same type of sensor; R

[0054] The residual value of the current period of the sensor is linearly fitted, and the slope value is obtained. The slope value is the drift characteristic value of the current period of the sensor. The linear fitting of the slope value is a prior art, which will not be described here.

[0055] Similarly, the residual values of the data sequences of other types of sensors in the grain storage environment monitoring system are calculated, and the drift characteristic values of the current period of the data collected by different types of sensors are extracted.

[0056] S2, by comparing the absolute value of the drift characteristic value of the current period of the data collected by each sensor with the preset threshold value, determining the sensor greater than or equal to the threshold value; the sensor is taken as an abnormal sensor, and a sensor group containing the abnormal sensor and the sensors associated with the abnormal sensor is established;

[0057] If the abnormal sensor is a temperature detection sensor, the temperature detection sensor is taken as the center of the sphere, the distance between the temperature detection sensor and the temperature detection sensor closest to one side is taken as the radius, and all the temperature detection sensors in the sphere are taken as the sensor group one.

[0058] If the abnormal sensor is a humidity detection sensor, the humidity detection sensor, the temperature detection sensor and the gas detection sensor are taken as the sensor group two.

[0059] If the abnormal sensor is a vibration detection sensor, the vibration detection sensor, the insect detection instrument and the infrared monitoring camera are taken as the sensor group three.

[0060] If the abnormal sensor is an insect detection instrument, the insect detection instrument, the temperature detection sensor and the humidity detection sensor are taken as the sensor group four.

[0061] S3, based on the sensor group of the abnormal sensor, the collection data or the drift characteristic value of each type of sensor in the same period in the sensor group is obtained, the correlation analysis is carried out by fusing the multi-sensor data, and the environmental interference or the real grain storage anomaly is distinguished, which specifically includes:

[0062] a, when the abnormal sensor is a temperature detection sensor, the drift characteristic values of each temperature detection sensor in the same period in the sensor group one are obtained, and compared with a temperature drift threshold value, if the absolute values of the drift characteristic values of two or more temperature detection sensors are greater than the temperature drift threshold value, it is a real grain storage abnormality, that is, the temperature imbalance in the grain depot; if only the absolute value of the drift characteristic value of the abnormal sensor is greater than the temperature drift threshold value, it is environmental interference.

[0063] b, when the abnormal sensor is a humidity detection sensor, the collection data of each type of sensor in the sensor group two are obtained, and the correlation analysis is performed by fusing the multi-sensor data, and the operation is specifically as follows:

[0064] If the humidity detection value of the humidity detection sensor decreases and the temperature detection value of the temperature detection sensor increases, the relative humidity decreases, and the humidity detection sensor signal is distorted; if the current time is in summer, it is a real grain storage abnormality, the grain temperature rises in summer, the relative humidity decreases, and the grain actually has a risk of moisture return;

[0065] If the humidity detection value of the humidity detection sensor increases, the temperature detection value of the temperature detection sensor increases, and the CO2 detection concentration of the gas detection sensor increases and the O2 detection concentration decreases, it is a real grain storage abnormality, that is, the grain is moldy;

[0066] If only the absolute value of the drift characteristic value of the abnormal sensor is greater than the humidity drift threshold value, it is environmental interference.

[0067] c, when the abnormal sensor is a vibration detection sensor, the collection data of each type of sensor in the sensor group three are obtained, and the correlation analysis is performed by fusing the multi-sensor data, and the operation is specifically as follows:

[0068] If the vibration detection value of the vibration detection sensor increases, the pest detection density of the pest monitoring instrument increases or the image recognition of the infrared monitoring camera is abnormal, it is a real grain storage abnormality, that is, there is a pest;

[0069] If only the absolute value of the drift characteristic value of the abnormal sensor is greater than the vibration drift threshold value, it is environmental interference.

[0070] d, when the abnormal sensor is a pest monitoring instrument, the collection data of each type of sensor in the sensor group four are obtained, and the correlation analysis is performed by fusing the multi-sensor data, and the operation is specifically as follows:

[0071] If the pest detection density of the pest monitoring instrument increases, and the temperature detection value of the temperature detection sensor increases, and the humidity detection value of the humidity detection sensor increases, it is a real grain storage abnormality, indicating that the pest outbreak, the pest reproduction releases heat, causing the local temperature to rise, promoting the grain respiration to increase, resulting in the humidity to increase;

[0072] If only the absolute value of the drift feature value of the abnormal sensor is greater than the density drift threshold, it is an environmental disturbance.

[0073] S4, triggering a hierarchical response according to the type of the real grain storage anomaly;

[0074] When the grain storage environment monitoring system detects a real grain storage anomaly, the Internet of Things management platform will start a hierarchical response according to the type of the anomaly and the number of anomalies, which specifically includes:

[0075] If there is only one real grain storage anomaly, a three-level response is triggered.

[0076] The three-level response is specifically automatic regulation according to the problem of the real grain storage anomaly, starting directional ventilation or starting temperature and humidity balancing method; and marking a yellow warning area on the Internet of Things management platform, repeating monitoring based on a fixed time period, and rechecking the real grain storage anomaly.

[0077] If there are two real grain storage anomalies or the three-level response continues to be eliminated, a two-level response is triggered; the two-level response operation is that the Internet of Things management platform automatically dispatches a patrol robot to collect grain samples in the abnormal grain storage area, and the Internet of Things management platform generates a disposal recommendation report according to the collected grain samples and pushes it to an expert decision end.

[0078] If there are more than two real grain storage anomalies, a one-level response is triggered, indicating that there is a major grain storage accident risk in the grain storage; the one-level response specifically includes that the Internet of Things management platform automatically locks the door of the abnormal grain storage, prohibits warehouse operation, and reports a warning to the grain storage watch group and the supervision center; and according to the type of the real grain storage anomaly, a disposal scheme is started respectively, for the type of temperature imbalance in the grain storage, full-warehouse circulation ventilation is started; for the type of grain mildew, dispatching conveying equipment to unload the grain is started; for the type of insect outbreak, phosphide is released to kill pests.

[0079] Then, the embodiment also provides a grain storage anomaly monitoring system, which includes:

[0080] The feature extraction module is configured to obtain the collection data of the multi-dimensional sensors in the grain storage, perform residual calculation on the data sequence of each sensor, and extract the drift feature value of the current period of the collection data of each sensor.

[0081] The comparison module is configured to compare the absolute value of the drift feature value of the current period of the collection data of each sensor with the preset threshold value through the preset threshold value, determine the sensor greater than or equal to the threshold value, take the sensor as an abnormal sensor, and establish a sensor group including the abnormal sensor and the sensors associated with the abnormal sensor.

[0082] The analysis processing module is configured to acquire the collected data or the drift characteristic values of the same type of sensors in the same period based on the sensor group of the abnormal sensor, perform correlation analysis on the multi-sensor data, and distinguish between environmental interference or real grain storage abnormality.

[0083] The abnormal response module is configured to trigger a hierarchical response according to the abnormal type of the real grain storage abnormality

[0084] In addition, a grain storage abnormality monitoring device for a granary is also provided, which comprises a processor and a memory, wherein the processor implements the grain storage abnormality monitoring method as described above when executing the computer program stored in the memory.

[0085] Finally, a computer readable storage medium for storing a computer program is also provided, wherein the computer program implements the grain storage abnormality monitoring method as described above when executed by the processor.

Claims

1. A method for monitoring abnormal grain storage in grain warehouses, characterized in that, include: The process involves acquiring data from multiple sensors within the grain silo, performing residual calculations on the data sequences from each sensor, and extracting the drift characteristic values ​​for the current time period from the data collected by each sensor. The specific steps are as follows: The residual value is obtained by subtracting the sensor's current data collection value from the reference value based on the sensor's corresponding reference value. Obtain the residual values ​​of the same type of sensors for the current time period, and calculate the mean and standard deviation of the residuals; The residual values ​​are standardized based on the residual mean and residual standard deviation; Linear fitting is performed on the standardized residual values ​​of the sensor data sequences for each time period to obtain the slope value, which is the drift characteristic value of the sensor data for the current time period. By using a preset threshold, the absolute value of the drift characteristic value of the data collected by each sensor in the current time period is compared with the preset threshold to determine the sensors that are greater than or equal to the threshold. Using this sensor as an anomaly sensor, a sensor group is established that includes the anomaly sensor and sensors associated with it, including: If the abnormal sensor is a temperature detection sensor, then draw a sphere with the temperature detection sensor as the center and the distance between the temperature detection sensor and the nearest temperature detection sensor on one side as the radius, and take all the temperature detection sensors in the sphere as sensor group one; If the abnormal sensor is a humidity detection sensor, then the humidity detection sensor, temperature detection sensor, and gas detection sensor will be used as sensor group two. If the abnormal sensor is a vibration detection sensor, then the vibration detection sensor, the insect pest monitoring instrument, and the infrared monitoring camera will be used as sensor group three. If the abnormal sensor is an insect pest monitoring instrument, then the insect pest monitoring instrument, temperature detection sensor, and humidity detection sensor will be grouped as sensor group four. Based on the sensor group of anomaly sensors, the data collected or drift characteristic values ​​of various types of sensors in the same time period are obtained, and the data of multiple sensors are fused to perform correlation analysis to distinguish between environmental interference and real grain storage anomalies. A tiered response is triggered based on the type of actual grain storage anomaly.

2. The method for monitoring abnormal grain storage in a grain warehouse according to claim 1, characterized in that, The formula for standardizing the residual values ​​is as follows: ， In the formula, R t R represents the residual value of the sensor during the current time period. t std This represents the standardized residual value of the sensor for the current time period; μ R This represents the mean residual value of sensors of the same type. σ R This represents the standard residual value for sensors of the same type.

3. The method for monitoring abnormal grain storage in a grain warehouse according to claim 1, characterized in that, The process of fusing multi-sensor data for correlation analysis to distinguish between environmental interference and actual grain storage anomalies specifically involves: When the abnormal sensor is a temperature detection sensor, the drift characteristic values ​​of each temperature detection sensor in the same time period within the sensor group are obtained and compared with the temperature drift threshold. If the absolute values ​​of the drift characteristic values ​​of two or more temperature detection sensors are greater than the temperature drift threshold, it is a real grain storage abnormality, that is, the temperature in the grain warehouse is unbalanced; if the absolute value of the drift characteristic value of only the abnormal sensor is greater than the temperature drift threshold, it is an environmental interference. When the abnormal sensor is a humidity detection sensor, if the humidity detection value of the humidity detection sensor decreases and the temperature detection value of the temperature detection sensor increases, it indicates a decrease in relative humidity and distortion of the humidity detection sensor signal. If the current time is summer, it indicates a real grain storage abnormality. If the humidity detection value of the humidity sensor increases, the temperature detection value of the temperature sensor increases, and the CO2 detection concentration of the gas sensor increases while the O2 detection concentration decreases, then it indicates a genuine grain storage anomaly.

4. The method for monitoring abnormal grain storage in a grain warehouse according to claim 1, characterized in that, The method of fusing multi-sensor data for correlation analysis to distinguish between environmental interference and actual grain storage anomalies also includes: When the abnormal sensor is a vibration detection sensor, if the vibration detection value of the vibration detection sensor increases, the pest detection density of the pest monitoring instrument increases, or the image recognition of the infrared monitoring camera is abnormal, then it is a real grain storage abnormality, that is, there is pest infestation; if only the absolute value of the drift characteristic value of the abnormal sensor is greater than the vibration drift threshold, then it is environmental interference. If the abnormal sensor is an insect pest monitoring instrument, and the insect pest detection density of the insect pest monitoring instrument increases, and the temperature detection value of the temperature detection sensor increases, and the humidity detection value of the humidity detection sensor increases, then it is a real grain storage abnormality; if only the absolute value of the drift characteristic value of the abnormal sensor is greater than the density drift threshold, then it is an environmental interference.

5. The method for monitoring abnormal grain storage in a grain warehouse according to claim 1, characterized in that, The specific operation of triggering a tiered response based on the anomaly type of the actual grain storage anomaly is as follows: If only one genuine grain storage anomaly exists, a Level 3 response will be triggered; If two genuine grain storage anomalies exist or the Level 3 response remains ineffective, a Level 2 response will be triggered. If two or more actual grain storage anomalies are found, a Level 1 response will be triggered.

6. A grain storage anomaly monitoring system for implementing the grain storage anomaly monitoring method according to claim 1, characterized in that, include: The feature extraction module is used to acquire data collected by multi-dimensional sensors in the grain warehouse, perform residual calculation on the data sequences of each sensor, and extract the drift feature values ​​of the data collected by each sensor in the current time period. The comparison module is used to compare the absolute value of the drift characteristic value of the data collected by each sensor in the current time period with the preset threshold, and to identify the sensor that is greater than or equal to the threshold; the sensor is identified as an abnormal sensor, and a sensor group containing the abnormal sensor and the sensor associated with the abnormal sensor is established. The analysis and processing module is used to acquire the collected data or drift characteristic values ​​of various types of sensors within the sensor group at the same time period based on the abnormal sensor, and to perform correlation analysis by fusing multi-sensor data to distinguish between environmental interference and real grain storage anomalies. The anomaly response module is used to trigger a tiered response based on the anomaly type of the actual grain storage anomaly.

7. A grain storage anomaly monitoring device, characterized in that, It includes a processor and a memory, wherein the processor executes a computer program stored in the memory to implement a grain storage anomaly monitoring method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, Used to store a computer program, wherein the computer program, when executed by a processor, implements a grain storage anomaly monitoring method as described in any one of claims 1-5.

Images