Grain storage cable interlayer temperature abnormity monitoring method and system

Abstract

The invention discloses a temperature anomaly monitoring method and system for a grain storage cable interlayer, and relates to the field of temperature anomaly monitoring, and the method comprises the steps: calculating a temperature gradient value and a temperature change rate between adjacent detection points based on real-time temperature data; determining a feature vector of each detection point; calculating an abnormal score corresponding to each detection point; extracting feature vectors of all detection points in a preset range with the abnormal detection point as the center; calculating temperature distribution morphological characteristics; when the similarity with the grain spontaneous heating mode is greater than a preset second threshold value, generating grain spontaneous heating early warning information; and when the similarity with the external environment factor mode is greater than a preset second threshold value, generating environment factor early warning information. The method is used for improving the efficiency and accuracy of grain storage management.

Description

Technical Field

[0001] This application belongs to the field of temperature anomaly monitoring, and particularly relates to a method and system for monitoring temperature anomalies in the cable interlayer of grain storage warehouses. Background Art

[0002] In the grain storage industry, temperature monitoring during the grain storage process is an important link to ensure the quality and safety of grain storage. Traditional methods for monitoring grain storage temperature mainly rely on manual inspections or single-point temperature measurement devices. This method has problems such as large monitoring blind spots, poor real-time performance, and high labor costs, making it difficult to detect and handle temperature anomalies during the grain stacking process in a timely manner, and easily causing a decline in grain quality and potential safety hazards.

[0003] In related technologies, an intelligent cable temperature monitoring system can be adopted. This system integrates a high-precision digital temperature sensor array in the cable interlayer and is equipped with a wireless transmission module, enabling real-time collection and remote monitoring of multi-point temperature data. This technology breaks through the limitations of traditional temperature measurement methods, not only capable of providing high-density and high-precision temperature monitoring data, but also able to achieve intelligent early warning of temperature anomalies through big data analysis, improving the safety management level of grain storage.

[0004] However, the above-mentioned related technologies are difficult to identify and distinguish temperature anomalies caused by the heat generation of the grain itself from temperature fluctuations caused by external environmental factors (such as direct sunlight, local rain leakage, etc.). This makes it easy to generate false alarms during temperature anomaly early warning, which may lead to unnecessary grain transfer or adjustment operations, reducing the efficiency and accuracy of grain storage management. Summary of the Invention

[0005] This application provides a method and system for monitoring temperature anomalies in the cable interlayer of grain storage warehouses, aiming to improve the efficiency and accuracy of grain storage management.

[0006] In the first aspect, this application provides a method for monitoring temperature anomalies in the cable interlayer of grain storage warehouses. Real-time temperature data of multiple detection points are collected through a temperature sensor array arranged in the cable interlayer, and the temperature sensor array is distributed in a spiral pattern along the cable interlayer; Based on the real-time temperature data, calculate the temperature gradient value and temperature change rate between adjacent detection points; Determine the feature vector of each detection point. The dimensions of the feature vector include the current temperature value of the detection point, the temperature gradient value with adjacent detection points, the temperature change rate, and the spatial position coordinates of the detection point; Calculate the anomaly score corresponding to each detection point according to the feature vector of each detection point and the temperature anomaly scoring function; When an anomaly detection point with an anomaly score exceeding a preset first threshold is detected, extract the feature vectors of all detection points within a preset range centered on the anomaly detection point; Calculate the temperature distribution morphological characteristics within a preset range based on the extracted feature vector; According to the pre-established temperature distribution morphology feature library, the temperature distribution morphology features are matched with the typical temperature distribution patterns caused by grain self-heating and external environmental factors to obtain the similarity with the typical temperature distribution pattern. The typical temperature distribution pattern includes the grain self-heating pattern and the external environmental factor pattern. When the similarity with the grain spontaneous heating pattern is greater than the preset second threshold, grain spontaneous heating warning information is generated; when the similarity with the external environmental factor pattern is greater than the preset second threshold, environmental factor warning information is generated.

[0007] By adopting the above technical solution, the temperature distribution data in the cable interlayer can be fully collected by spirally arranging the temperature sensor array in the cable interlayer. The temperature gradient value and change rate are calculated based on the real-time temperature data, and the feature vector is constructed in combination with the spatial position of the detection point, so that the system can characterize the temperature characteristics of each detection point from multiple dimensions. The abnormal detection point can be accurately identified by calculating the abnormal score through the temperature anomaly scoring function. After the abnormal detection point is found, the system can grasp the overall temperature distribution law of the abnormal area by extracting the feature vector of the detection point within the surrounding preset range and analyzing the temperature distribution morphological characteristics. The obtained temperature distribution morphological characteristics are matched with the pre-established typical temperature distribution pattern to distinguish whether the temperature anomaly is caused by self-heating of grain or external environmental factors, thereby generating the corresponding type of early warning information, improving the accuracy and reliability of temperature anomaly monitoring, enabling the system to timely discover safety hazards in the grain storage process and take targeted prevention and control measures, thereby improving the efficiency and accuracy of grain storage management.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, the temperature anomaly scoring function is: In the above function, S is the abnormality score, T is the current temperature value of the detection point, T0 is the historical normal temperature benchmark value, and T ref is the reference temperature difference, L is the characteristic length, is the temperature gradient value, ε is a small positive number, τ is the time scale, d i is the distance to the adjacent detection point, R is the distance, T i is the temperature value of the adjacent point, N is the set of adjacent points, α, λ1, λ2, λ3, β, γ, θ and η are weight coefficients, is the rate of temperature change.

[0009] By adopting the above technical solutions, the temperature anomaly scoring function comprehensively considers the temperature deviation, temperature gradient, temperature change rate of the detection point, and the temperature relationship with adjacent detection points. The first term in the function reflects the degree of temperature anomaly at the detection point by normalizing the deviation between the current temperature and the historical reference value. The second and third terms respectively characterize the temperature change characteristics in the spatial and temporal dimensions and can detect sudden temperature anomalies. The fourth term calculates the temperature difference between the detection point and surrounding detection points, considering the attenuation effect of spatial distance, and can identify local temperature anomaly phenomena. The fifth term introduces the second-order derivative information of the temperature field to detect the mutation characteristics of the temperature distribution. By reasonably setting the weight coefficients of each term, this scoring function can accurately quantify the degree of temperature anomaly at each detection point, reduce the false alarm rate, and improve the recognition sensitivity to different types of temperature anomalies.

[0010] In combination with some embodiments of the first aspect, in some embodiments, based on the extracted feature vectors, the temperature distribution morphological features within a preset range are calculated, specifically including: According to the spatial position coordinates and temperature data of the anomaly detection points included in the extracted feature vectors, a continuous temperature field distribution function is established; The gradient vector field of the continuous temperature field distribution function is calculated to obtain the temperature change direction and change intensity of each detection point within the preset range; Isothermal surfaces are extracted from the continuous temperature field distribution function, and the temperature contour line set is determined through the intersection lines of the isothermal surfaces and the preset plane; the shape characteristic parameters of the temperature contour line set are calculated; The evolution characteristics of the continuous temperature field distribution function in the time dimension are analyzed, and based on the evolution characteristics, the diffusion rate vector of the temperature field, the expansion direction and expansion speed of the abnormal area are calculated; The shape characteristic parameters, diffusion rate vector, expansion direction and expansion speed are combined to form the temperature distribution morphological features.

[0011] By adopting the above technical solutions, a continuous temperature field distribution function is established based on the feature vectors, and the complete temperature distribution of the abnormal area can be restored. By calculating the gradient vector field of the temperature field, the direction and intensity information of the temperature change are obtained. Extracting the isothermal surfaces and determining the temperature contour line set can intuitively characterize the spatial structure characteristics of the temperature field. Combining the shape characteristic parameters of the temperature contour lines and the time evolution characteristics of the temperature field, the system can accurately describe the geometric characteristics, diffusion characteristics and development trend of the temperature abnormal area. This method for extracting temperature distribution morphological features converts discrete temperature data into a continuous temperature field description, realizes the precise characterization of the temperature abnormal area, and enables the subsequent pattern matching analysis to more accurately identify the causes of temperature anomalies.

[0012] In some embodiments in combination with some embodiments of the first aspect, calculating the shape feature parameters of the set of temperature isotherms specifically includes: Calculating the area, perimeter, and circularity of each isotherm in the set of temperature isotherms; Extracting the spacing data between adjacent isotherms in the set of temperature isotherms; Calculating the mean and standard deviation of the spacing data; Counting the number of nested layers of isotherms in the set of temperature isotherms; Combining the area, perimeter, circularity, mean spacing, standard deviation of spacing, and number of nested layers to form shape feature parameters.

[0013] By adopting the above technical solution, by calculating the area, perimeter, and circularity of the set of temperature isotherms, the geometric shape characteristics of the temperature anomaly region can be quantitatively described. Analyzing the spacing data between adjacent isotherms and its statistical characteristics reflects the spatial gradient distribution law of the temperature field. Counting the number of nested layers of isotherms characterizes the hierarchical structure characteristics of the temperature anomaly region. These shape feature parameters are combined with each other to form a comprehensive set of feature parameters, which can distinguish the temperature anomaly distribution patterns caused by different causes. This feature extraction method quantitatively expresses the geometric features, spacing features, and structural features of the temperature isotherms, enhances the distinguishability of the temperature distribution morphological features, and improves the accuracy of subsequent pattern matching analysis.

[0014] In some embodiments in combination with some embodiments of the first aspect, after generating the environmental factor warning information when the similarity with the external environmental factor pattern is greater than a preset second threshold, the method further includes: Obtaining the real-time temperature data of all detection points within a preset detection radius around the anomaly detection point; Calculating the temperature spatial distribution characteristics within the preset detection radius, where the temperature spatial distribution characteristics include the shape characteristics of the temperature isotherms, the spatial position characteristics of the temperature maximum points, and the direction characteristics of the temperature gradient; When the temperature isotherm presents a closed ring shape and the temperature gradient direction points to the center of the ring, the ring-shaped area is determined as the diffusion range; when the temperature isotherm presents a band shape and the temperature gradient direction expands horizontally, the band-shaped area is determined as the diffusion range; Calculating the temperature anomaly duration and temperature cumulative deviation value within the diffusion range; Calculating the environmental factor hazard degree according to the temperature anomaly duration, temperature cumulative deviation value, and the area of the diffusion range; When the hazard degree exceeds a preset third threshold, setting the level of the environmental factor warning information to an emergency warning; When the hazard degree is lower than a preset fourth threshold, setting the level of the environmental factor warning information to a general warning, where the preset third threshold is greater than the preset fourth threshold.

[0015] By adopting the above technical solution, by obtaining the real-time temperature data of the detection points within the preset detection radius around the anomaly detection point, and combining the shape features of the temperature isotherm, the spatial position features of the temperature maximum point, and the temperature gradient direction features, the diffusion form of the temperature anomaly area can be accurately identified. According to the closed circular or strip features of the temperature isotherm and the temperature gradient direction, the actual temperature anomaly diffusion range can be accurately defined. By calculating the duration of the temperature anomaly and the temperature cumulative deviation value within the diffusion range, the severity of the temperature anomaly can be quantitatively evaluated. Considering multiple-dimensional indicators such as the duration, the cumulative deviation value, and the area of the diffusion range, the actual harm degree of the environmental factors can be scientifically calculated. By comparing the harm degree with the preset threshold, the system can automatically determine the urgency level of the warning level, thereby realizing the hierarchical warning of the temperature anomaly caused by environmental factors. This multi-dimensional evaluation and hierarchical warning mechanism enables the system to accurately distinguish temperature anomaly situations of different severity levels, avoid problems of over-warning or under-warning, and helps warehouse management personnel take prevention and control measures adapted to the actual harm degree.

[0016] Combined with some embodiments of the first aspect, in some embodiments, calculating the duration of the temperature anomaly and the temperature cumulative deviation value within the diffusion range specifically includes: Obtain the historical temperature data of all detection points within the diffusion range; Calculate the temperature mean and standard deviation of the historical temperature data in different time periods; Determine the normal range of temperature fluctuations according to the temperature mean and standard deviation, and use the temperature mean plus or minus twice the standard deviation as the upper threshold and the lower threshold of the normal range respectively; Count the duration of the real-time temperature data of the detection points within the diffusion range that exceeds the upper threshold or is lower than the lower threshold, and take the longest duration as the duration of the temperature anomaly; Calculate the difference between the temperature value of the real-time temperature data of the detection points within the diffusion range that exceeds the upper threshold and the upper threshold, or the difference between the temperature value that is lower than the lower threshold and the lower threshold; Take the integral value of the difference over time as the temperature cumulative deviation value.

[0017] By adopting the above technical solutions, by analyzing the historical temperature data of the detection points within the diffusion range, calculating the temperature mean value and standard deviation in different time periods, a dynamic benchmark of temperature fluctuation can be established. By statistically analyzing the duration of the real-time temperature data exceeding the threshold, the persistence of temperature anomalies can be accurately quantified. Calculating the difference between the temperature exceeding the threshold and performing time integration, the obtained temperature cumulative deviation value can comprehensively reflect the intensity and cumulative effect of temperature anomalies. This evaluation method based on establishing a dynamic benchmark threshold with historical data and combining the dual indicators of duration and cumulative deviation enables the system to adapt to the temperature fluctuation characteristics in different storage environments, improves the recognition accuracy of temperature anomalies, and reduces the possibility of false alarms and missed alarms. At the same time, the calculation of the temperature cumulative deviation value takes into account the comprehensive influence of the intensity and duration of temperature anomalies, and can more objectively reflect the actual threat degree of temperature anomalies to storage safety.

[0018] Combined with some embodiments of the first aspect, in some embodiments, the environmental factor hazard degree is calculated according to the temperature anomaly duration, the temperature cumulative deviation value, and the area of the diffusion range, specifically including: Obtain the preset reference duration, the preset reference cumulative deviation value, and the preset reference area; Divide the temperature anomaly duration by the preset reference duration to obtain the time weight coefficient; Divide the temperature cumulative deviation value by the preset reference cumulative deviation value to obtain the temperature weight coefficient; Divide the area of the diffusion range by the preset reference area to obtain the area weight coefficient; Take the sum of the product of the temperature anomaly duration and the time weight coefficient, the product of the temperature cumulative deviation value and the temperature weight coefficient, and the product of the area of the diffusion range and the area weight coefficient as the value corresponding to the environmental factor hazard degree.

[0019] By adopting the above technical solutions, by introducing the preset reference duration, the preset reference cumulative deviation value, and the preset reference area as standard reference values, the temperature anomaly duration, the temperature cumulative deviation value, and the area of the diffusion range obtained from actual monitoring are respectively calculated as ratios with their corresponding reference values to obtain the corresponding weight coefficients. This standardized processing method enables effective comprehensive evaluation of indicators with different dimensions. By adding the products of each indicator and its weight coefficient, a comprehensive score of the environmental factor hazard degree can be obtained. This scoring mechanism fully considers the three key dimensions of the persistence, intensity, and spatial influence range of temperature anomalies, making the calculation result of the hazard degree have a clear physical meaning. Based on the dynamic adjustment mechanism of the weight coefficient, the system can flexibly adjust the influence weights of each indicator according to the characteristics of different types of temperature anomalies, improving the pertinence and accuracy of the hazard degree evaluation. This quantitative evaluation method provides an objective basis for the early warning classification of temperature anomalies and helps to achieve the precise evaluation of the environmental factor hazard degree.

[0020] In a second aspect, an embodiment of the present application provides a temperature anomaly monitoring system for a cable interlayer in a grain storage warehouse. The temperature anomaly monitoring system for the cable interlayer in the grain storage warehouse includes: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program code. The computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, including instructions that, when run on a system, cause the system to execute the method described in the first aspect and any possible implementation manner in the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer program product that, when run on a system, causes the system to execute the method described in any possible implementation manner in the first aspect.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. The present application provides a method for monitoring temperature anomalies in a cable interlayer of a grain storage warehouse. By spirally arranging a temperature sensor array in the cable interlayer, temperature distribution data in the cable interlayer can be comprehensively collected. Based on real-time temperature data, temperature gradient values and change rates are calculated, and feature vectors are constructed in combination with the spatial positions of detection points, enabling the system to characterize the temperature characteristics of each detection point from multiple dimensions. By calculating anomaly scores through a temperature anomaly scoring function, abnormal detection points can be accurately identified. After discovering abnormal detection points, by extracting the feature vectors of detection points within a preset range around them and analyzing the temperature distribution pattern features, the system can master the overall temperature distribution law of the abnormal area. By performing a matching degree analysis on the obtained temperature distribution pattern features and a pre-established typical temperature distribution pattern, it is possible to distinguish whether the temperature anomaly is caused by self-heating of the grain or external environmental factors, thereby generating corresponding types of warning information, improving the accuracy and reliability of temperature anomaly monitoring, enabling the system to timely discover potential safety hazards during the grain storage process and take targeted prevention and control measures, and thus improving the efficiency and accuracy of grain storage management.

[0024] 2. The present application provides a method for monitoring temperature anomalies in grain storage cable interlayers. The temperature anomaly scoring function comprehensively considers the temperature deviation, temperature gradient, temperature change rate and temperature relationship of the detection point with the adjacent detection point. The first item in the function reflects the degree of temperature anomaly at the detection point by normalizing the deviation between the current temperature and the historical benchmark value. The second and third items characterize the temperature change characteristics in the spatial and temporal dimensions, respectively, and can detect sudden temperature anomalies. The fourth item calculates the temperature difference between the detection point and the surrounding detection points, taking into account the attenuation effect of spatial distance, and can identify local temperature anomalies. The fifth item introduces the second-order derivative information of the temperature field to detect the mutation characteristics of the temperature distribution. By reasonably setting the weight coefficients of each item, the scoring function can accurately quantify the degree of temperature anomaly at each detection point, reduce the false alarm rate, and improve the recognition sensitivity of different types of temperature anomalies.

[0025] 3. The present application provides a method for monitoring temperature anomalies in the interlayer of grain storage cables. By acquiring the real-time temperature data of the detection points within the preset detection radius around the abnormal detection point, combined with the shape characteristics of the temperature contour line, the spatial position characteristics of the temperature maximum point and the direction characteristics of the temperature gradient, the diffusion morphology of the temperature anomaly area can be accurately identified. According to the closed loop or band characteristics of the temperature contour line and the direction of the temperature gradient, the actual temperature anomaly diffusion range can be accurately defined. By calculating the duration of temperature anomalies and the cumulative temperature deviation value within the diffusion range, the severity of temperature anomalies can be quantitatively evaluated. Taking into account multi-dimensional indicators such as duration, cumulative deviation value and diffusion range area, the actual degree of harm of environmental factors can be scientifically calculated. By comparing the degree of harm with the preset threshold, the system can automatically determine the urgency of the warning level, thereby realizing the graded warning of temperature anomalies caused by environmental factors. This multi-dimensional evaluation and graded warning mechanism enables the system to accurately distinguish temperature anomalies of different severity, avoid the problem of excessive or insufficient warning, and help warehouse management personnel take prevention and control measures that are appropriate to the actual degree of harm. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flow chart of a method for monitoring abnormal temperature of a grain storage cable interlayer in an embodiment of the present application.

[0027] Figure 2 It is a flow chart of a method for evaluating the degree of hazard and grading early warning of temperature anomalies caused by external environmental factors in an embodiment of the present application.

[0028] Figure 3 It is a schematic diagram of the physical device structure of a temperature anomaly monitoring system for a grain storage cable interlayer provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The terms used in the following embodiments of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. As used in the specification and appended claims of this application, the singular forms "a", "an", "the", "above", "said", "this" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in this application refers to any or all possible combinations of one or more of the listed items.

[0030] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of this application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0031] The following uses an embodiment and combines Figure 1 , to describe a method for monitoring abnormal temperature in a cable interlayer of a grain storage warehouse in the embodiments of this application: Please refer to Figure 1 , which is a schematic flowchart of a method for monitoring abnormal temperature in a cable interlayer of a grain storage warehouse in the embodiments of this application.

[0032] S101. Collect real-time temperature data of multiple detection points through a temperature sensor array arranged in the cable interlayer; the system collects real-time temperature data of multiple detection points through a temperature sensor array arranged in the cable interlayer, and the temperature sensor array is distributed in a spiral shape along the cable interlayer. In this step, the system uses a temperature sensor array arranged in the cable interlayer to collect real-time temperature data of multiple detection points. The temperature sensor array can adopt different types of temperature sensors, such as thermocouples, thermal resistors, thermistors, etc., and is selected according to specific application scenarios and measurement accuracy requirements. The arrangement method of the temperature sensors can be optimized according to the structural characteristics and monitoring requirements of the cable interlayer to achieve comprehensive coverage and accurate measurement of the temperature field of the cable interlayer.

[0033] Specifically, the temperature sensor array can be distributed in a spiral shape along the cable interlayer, that is, the temperature sensors are evenly distributed along the axial and circumferential directions of the cable interlayer, forming a spiral arrangement pattern. This arrangement method can effectively improve the spatial resolution of temperature monitoring and capture local temperature anomalies in the cable interlayer. At the same time, the system can also optimize the number and spacing of temperature sensors according to parameters such as the length and diameter of the cable interlayer to balance monitoring accuracy and cost.

[0034] S102, calculating the temperature gradient value and temperature change rate between adjacent detection points based on the real-time temperature data; In this step, the system calculates the temperature gradient value and temperature change rate between adjacent detection points based on the real-time temperature data collected. The temperature gradient value reflects the spatial variation characteristics of the temperature distribution in the cable interlayer, while the temperature change rate characterizes the temperature change trend over time. By calculating these two indicators, the temperature distribution state and dynamic evolution process in the cable interlayer can be comprehensively evaluated.

[0035] Specifically, the system can use the method of numerical differentiation to calculate the temperature gradient value. For each detection point, select several adjacent detection points, use the finite difference method to calculate the partial derivative of the temperature in space, and obtain the temperature gradient vector at the point.

[0036] S103, determining a feature vector of each detection point, and calculating an anomaly score corresponding to each detection point according to the feature vector of each detection point and a temperature anomaly scoring function; The system determines the feature vector of each detection point. The dimensions of the feature vector include the current temperature value of the detection point, the temperature gradient value with adjacent detection points, the temperature change rate, and the spatial position coordinates of the detection point. The system calculates the anomaly score corresponding to each detection point based on the feature vector of each detection point and the temperature anomaly scoring function. The temperature anomaly scoring function is: In the above function, S is the abnormality score, T is the current temperature value of the detection point, T0 is the historical normal temperature benchmark value, and T ref is the reference temperature difference, L is the characteristic length, is the temperature gradient value, ε is a small positive number, τ is the time scale, d i is the distance to the adjacent detection point, R is the distance, T i is the temperature value of the adjacent point, N is the set of adjacent points, α, λ1, λ2, λ3, β, γ, θ and η are weight coefficients, is the rate of temperature change.

[0037] In this step, the system comprehensively considers multiple factors that affect temperature anomalies by determining the feature vector of each detection point. The dimensions of the feature vector include key parameters such as the current temperature value of the detection point, the temperature gradient value with adjacent detection points, the temperature change rate, and the spatial position coordinates of the detection point. These parameters reflect the degree of abnormality of the temperature of the detection point from different angles, such as the absolute value of the temperature, the spatial temperature change rate, the time temperature change rate, and the temperature distribution of surrounding points. By combining these parameters into a feature vector, the temperature anomaly characteristics of each detection point can be more comprehensively characterized.

[0038] When calculating the anomaly score, the system uses a scoring function that comprehensively considers multiple anomaly features. By setting the weight coefficients of different features, this function can flexibly adjust the importance of different anomaly factors. For example, by adjusting the magnitudes of λ1, λ2, and λ3, the impacts of the absolute temperature, the spatial temperature change rate, and the temporal temperature change rate on the anomaly score can be controlled respectively; by adjusting β and γ, the influence intensity and decay rate of the temperature distribution difference among surrounding points can be controlled; by adjusting θ and η, the influence of the second-order temperature derivative can be controlled. The settings of these parameters can be adjusted and optimized according to the actual application scenarios and experience to achieve better anomaly detection effects.

[0039] S104. When an anomaly detection point with an anomaly score exceeding a preset first threshold is detected, extract the feature vectors of all detection points within a preset range centered on the anomaly detection point; In this step, after detecting an anomaly point, the temperature distribution data in its surrounding area is further extracted to prepare for subsequent analysis of the anomaly cause and temperature evolution trend. When the anomaly score of a certain detection point exceeds the preset threshold, this point can be preliminarily determined as an anomaly point. However, the anomaly of a single point cannot fully reflect the real anomaly situation, and it may be a false alarm caused by reasons such as sensor errors. To improve the accuracy of judgment, the system extracts the data of all detection points within a preset range around the anomaly point. By analyzing the overall temperature distribution characteristics of this area, the authenticity of the anomaly occurrence can be judged more reliably, and more abundant information can be provided for the next step of analyzing the anomaly cause.

[0040] The feature vectors of the surrounding points can be extracted using the same dimension and calculation method as the single-point feature vectors, obtaining a set of feature vector groups reflecting the temperature distribution in the local area. These feature vectors contain important information such as the spatial temperature distribution and temporal evolution trend of this area. The system can flexibly set the size of the extraction range, which should be large enough to contain sufficient anomaly information and not too large to introduce too much irrelevant data and interfere with the judgment. At the same time, the extraction range can also be dynamically adjusted according to factors such as the density and layout of the detection points.

[0041] S105. Calculate the temperature distribution morphological features within the preset range based on the extracted feature vectors; The system calculates the temperature distribution pattern features within a preset range based on the extracted feature vectors, specifically including: establishing a continuous temperature field distribution function according to the spatial position coordinates and temperature data of the anomaly detection points included in the extracted feature vectors; calculating the gradient vector field of the continuous temperature field distribution function to obtain the temperature change direction and change intensity of each detection point within the preset range; extracting isothermal surfaces in the continuous temperature field distribution function, and determining the temperature contour line set through the intersection lines of the isothermal surfaces and the preset plane; calculating the shape feature parameters of the temperature contour line set, specifically including: calculating the area, perimeter, and circularity of each contour line in the temperature contour line set; extracting the spacing data between adjacent contour lines in the temperature contour line set; calculating the mean and standard deviation of the spacing data; and counting the number of nested layers of the contour lines in the temperature contour line set. Combining the area, perimeter, circularity, mean spacing, spacing standard deviation, and number of nested layers to form the shape feature parameters; analyzing the evolution characteristics of the continuous temperature field distribution function in the time dimension, and calculating the diffusion rate vector of the temperature field, the expansion direction, and the expansion speed of the abnormal area based on the evolution characteristics; combining the shape feature parameters, diffusion rate vector, expansion direction, and expansion speed to form the temperature distribution pattern features.

[0042] After obtaining the feature vectors of all detection points within the abnormal area, this step further analyzes the temperature distribution pattern features of this area. The temperature distribution pattern reflects the spatial distribution law and evolution trend of the occurrence of anomalies, and is of great significance for judging the causes of anomalies and predicting the development of anomalies. The system depicts the morphological characteristics of the temperature distribution from different perspectives through multiple steps and multiple feature indicators.

[0043] First, the system establishes a continuous temperature field distribution function based on the positions and temperature data of the detection points. This function can map the discrete detection point temperatures to a continuous space through mathematical methods such as interpolation and fitting, obtaining the temperature distribution throughout the region. This provides convenience for subsequent analysis.

[0044] Then, the system calculates the gradient vector field of the temperature field to obtain the direction and intensity of temperature change at each position. The gradient reflects the rate of temperature change in space and can be used to judge the boundaries and expansion directions of abnormal areas. In addition, the system also extracts isothermal surfaces in the temperature field, and obtains a series of temperature contour lines through the intersection lines of the isothermal surfaces and the preset plane. The temperature contour lines visually display the spatial morphology of the temperature distribution, and the contour lines of different temperature values form a distribution feature similar to a topographic map.

[0045] Next, the system calculates the shape feature parameters of the temperature isotherms from multiple aspects. Parameters such as area, perimeter, and circularity reflect the size, complexity, and regularity of the isotherm shape. The spacing data between adjacent isotherms, along with its mean and standard deviation, reflect the intensity and uniformity of the temperature change in space. The number of nested layers of the isotherms reflects the complexity of the temperature distribution and the extent of the abnormal area. These shape feature parameters characterize the spatial morphological characteristics of the temperature distribution from different aspects.

[0046] In addition to the spatial morphology, the system also analyzes the evolution characteristics of the temperature field over time. By calculating dynamic parameters such as the diffusion rate vector of the temperature field, the expansion direction and speed of the abnormal area, the development trend and change pattern of the abnormal area can be predicted.

[0047] Finally, the system combines the static shape feature parameters and the dynamic evolution feature parameters to obtain the complete morphological characteristics of the temperature distribution. These characteristic information can be used for subsequent abnormal pattern matching and early warning analysis.

[0048] S106. Analyze the matching degree between the temperature distribution morphological characteristics and the typical temperature distribution patterns caused by grain self-heating and external environmental factors according to the pre-established temperature distribution morphological characteristic library, and obtain the similarity with the typical temperature distribution pattern; the system analyzes the matching degree between the temperature distribution morphological characteristics and the typical temperature distribution patterns caused by grain self-heating and external environmental factors according to the pre-established temperature distribution morphological characteristic library, and obtains the similarity with the typical temperature distribution pattern. The typical temperature distribution patterns include the grain self-heating pattern and the external environmental factor pattern.

[0049] This step uses the pre-established characteristic library to perform pattern matching and similarity analysis on the temperature distribution morphology of the abnormal area. Temperature anomalies may be caused by various factors, such as grain self-heating, external environmental temperature changes, etc. Abnormalities caused by different causes have different characteristics in the temperature distribution morphology. By matching with the typical patterns, the most likely cause of the anomaly can be judged, providing a basis for subsequent early warning and disposal.

[0050] The temperature distribution morphological characteristic library is the corresponding relationship between the abnormal causes and the typical temperature distribution patterns summarized through a large amount of historical data and expert experience. The characteristic library contains the typical temperature distribution patterns of common abnormal causes such as grain self-heating and external environmental factors. Each pattern corresponds to a set of typical morphological feature parameters. These typical patterns can be extracted from historical abnormal data through data mining methods such as clustering and classification, or can be obtained through expert experience and theoretical analysis. The establishment of the characteristic library requires long-term data accumulation and knowledge precipitation, which is crucial for improving the accuracy of the system's anomaly judgment.

[0051] When performing pattern matching, the system compares the temperature distribution morphological features of the area to be analyzed with the typical patterns in the feature library one by one and calculates the similarity between them. The similarity can be calculated using common similarity measurement methods such as Euclidean distance and cosine similarity. In addition, since different feature parameters contribute differently to the similarity, the system can assign different weights to different features and comprehensively obtain the final similarity. The higher the similarity, the closer the temperature distribution of the area to be analyzed is to the typical pattern, and the greater the possibility of the cause of the anomaly.

[0052] Through pattern matching and similarity analysis, the system can find one or several typical patterns that are most similar to the temperature distribution of the area to be analyzed and judge the most likely cause of the anomaly. However, in practical applications, due to the complexity and diversity of abnormal situations, a single pattern may not be able to fully cover all abnormal situations. To improve the accuracy and reliability of the judgment, the system can adopt a multi-pattern fusion method. That is, instead of simply finding the single pattern with the highest similarity, it comprehensively considers multiple patterns with relatively high similarities and obtains a comprehensive judgment result of the cause of the anomaly through methods such as weighted average and voting. This multi-pattern fusion method can effectively avoid the one-sidedness of single-pattern judgment and improve the system's ability to handle complex abnormal situations.

[0053] S107: When the similarity with the grain self-heating pattern is greater than the preset second threshold, generate a grain self-heating warning message; when the similarity with the external environmental factor pattern is greater than the preset second threshold, generate an environmental factor warning message.

[0054] After obtaining the similarity between the abnormal area and the typical temperature distribution pattern, this step generates corresponding abnormal warning messages according to the similarity situation. The warning messages can prompt the location, severity, most likely cause, etc. of the anomaly, providing a decision-making basis for realizing automated and intelligent anomaly handling.

[0055] The system has separately set warning thresholds for the grain self-heating pattern and the external environmental factor pattern. When the similarity between the temperature distribution of the abnormal area and a certain pattern exceeds the corresponding threshold, it can be determined that the anomaly is caused by the corresponding cause of this pattern, and a corresponding warning message is generated. The setting of the threshold needs to balance the sensitivity and accuracy of the warning. Setting the threshold too low may lead to too many false alarms, while setting the threshold too high may miss some anomalies. Therefore, it is necessary to reasonably set the warning threshold according to the actual application requirements and historical anomaly data.

[0056] When generating warning information, the system should not only give the conclusion of the warning, but also provide the key information about the occurrence of the abnormality, such as the location range of the abnormal area, the central temperature value, the temperature change rate, etc., so that the staff can quickly locate and evaluate the abnormal situation. In addition, for different causes of abnormalities, the warning information should also include corresponding disposal suggestions, such as strengthening ventilation and cooling, adjusting the grain storage environment, etc., to guide the staff to take corresponding measures in time.

[0057] It should be noted that in actual applications, there may be a situation where the similarities of multiple abnormal patterns all exceed the warning threshold. This indicates that the abnormality may be the result of the combined action of multiple factors. In this case, the system can generate multiple warning information according to the similarity of different patterns and indicate their respective probabilities. This can provide more comprehensive reference information for abnormality disposal.

[0058] Considering the different degrees of urgency of abnormal situations, the system can also classify the warning information according to the severity of the abnormality. For example, multiple levels of warning thresholds can be set, and when the abnormal similarity exceeds different thresholds, warning information with different degrees of urgency is generated respectively. This can help the staff quickly judge the severity of the abnormality and reasonably allocate disposal resources and attention.

[0059] In some cases, due to reasons such as incomplete detection data and uncertain pattern matching, there may be certain uncertainties in abnormality judgment and warning. To avoid false alarms and missed alarms, when generating warning information, the system can also give an evaluation of the warning credibility. The credibility can comprehensively consider factors such as the length of the abnormal detection time, the gap between the similarity and the threshold, and the data quality, and use a confidence index to represent the credibility of the warning conclusion. This can help the staff more reasonably interpret the warning information and carry out manual review and judgment targeted.

[0060] In the above embodiments, by arranging the temperature sensor array in a spiral manner in the cable interlayer, the temperature distribution data in the cable interlayer can be comprehensively collected. Based on the real-time temperature data, the temperature gradient value and the change rate are calculated, and the eigenvector is constructed in combination with the spatial position of the detection point, so that the system can characterize the temperature characteristics of each detection point from multiple dimensions. By calculating the anomaly score through the temperature anomaly scoring function, the anomaly detection point can be accurately identified. After the anomaly detection point is found, by extracting the eigenvectors of the detection points within a preset range around it and analyzing the temperature distribution morphological characteristics, the system can master the overall temperature distribution law of the anomaly area. By performing a matching degree analysis on the obtained temperature distribution morphological characteristics and the pre-established typical temperature distribution patterns, it is possible to distinguish whether the temperature anomaly is caused by self-heating of the grain or external environmental factors, thereby generating corresponding types of warning information, improving the accuracy and reliability of temperature anomaly monitoring, enabling the system to timely discover potential safety hazards in the process of grain storage and take targeted prevention and control measures, and further improving the efficiency and accuracy of grain storage management.

[0061] The above embodiments mainly describe the detection of temperature anomalies and the process of identifying their types. When it is identified that the temperature anomaly is caused by external environmental factors, it is necessary to further evaluate its harm degree and determine the warning level in order to take corresponding prevention and control measures. Therefore, the embodiments of the present application also provide a method for evaluating the harm degree and warning classification of temperature anomalies caused by external environmental factors. The following combines Figure 2 , and describes a method for evaluating the harm degree and warning classification of temperature anomalies caused by external environmental factors in the embodiments of the present application: Please refer to Figure 2 , which is a schematic flow chart of a method for evaluating the harm degree and warning classification of temperature anomalies caused by external environmental factors in the embodiments of the present application.

[0062] S201. Obtain the real-time temperature data of all detection points within a preset detection radius range around the anomaly detection point; A circular area is formed. The system obtains the real-time temperature data of all detection points within this area as the input for subsequent analysis. The size of the preset detection radius can be adjusted according to the actual application scenario and requirements to balance the calculation efficiency and the accuracy of anomaly detection.

[0063] The system can obtain real-time temperature data through various sensors and data acquisition devices, such as temperature sensors, infrared thermal imagers, etc. These devices can be arranged at different positions in the monitoring area to form a temperature detection network. The system obtains temperature data from these devices regularly or in real time through wireless or wired communication methods and stores it in the database for use in subsequent steps.

[0064] S202. Calculate the temperature spatial distribution characteristics within the preset detection radius range; The system calculates the spatial distribution characteristics of temperature within a preset detection radius. The spatial distribution characteristics of temperature include the shape characteristics of isotherms, the spatial position characteristics of temperature maximum points, and the direction characteristics of temperature gradients.

[0065] In this step, the system performs spatial analysis on the acquired temperature data and calculates the spatial distribution characteristics of temperature within a preset detection radius. The spatial distribution characteristics of temperature reflect the variation law and trend of temperature in space and can provide an important basis for subsequent anomaly assessment. Common spatial distribution characteristics of temperature include the shape characteristics of isotherms, the spatial position characteristics of temperature maximum points, the direction characteristics of temperature gradients, etc.

[0066] The system can use spatial interpolation methods, such as Kriging interpolation or inverse distance weighted interpolation, to generate a continuous temperature field based on discrete temperature data. On the temperature field, the system extracts isotherms and analyzes their shape characteristics, such as whether they present a closed circular or banded structure. At the same time, the system identifies the local maximum points of the temperature field and records their spatial position coordinates. In addition, the system calculates the gradient vector of temperature in space to characterize the direction and rate of temperature change.

[0067] S203. When the isotherm presents a closed circular shape and the temperature gradient direction points to the center of the circle, the circular region is determined as the diffusion range; when the isotherm presents a banded shape and the temperature gradient direction extends horizontally, the banded region is determined as the diffusion range; this step determines the diffusion range of temperature anomalies according to the shape characteristics of isotherms and the direction characteristics of temperature gradients. The diffusion range represents the spatial area affected by temperature anomalies and is of great significance for evaluating the severity of anomalies and taking corresponding measures.

[0068] When the isotherm presents a closed circular shape and the temperature gradient direction points to the center of the circle, the system believes that this spatial distribution characteristic reflects the process of temperature anomaly spreading from the center to the surroundings, so the circular region is determined as the diffusion range. On the contrary, when the isotherm presents a banded shape and the temperature gradient direction extends horizontally along the banded region, the system believes that this spatial distribution characteristic reflects the process of temperature anomaly spreading along a specific direction, so the banded region is determined as the diffusion range.

[0069] When judging the diffusion range, the system can set temperature thresholds and shape parameters to quantitatively describe the closure of isotherms and the direction consistency of temperature gradients. For example, the system can calculate the maximum value of the temperature difference between the inside and outside of the circular region, and when it exceeds the preset threshold, it is considered that there is a significant temperature gradient direction. Similarly, the system can calculate the curvature and closure degree of the isotherm, and when it meets the preset conditions, it is considered to present a closed circular shape.

[0070] S204. Calculate the duration of temperature anomaly and the temperature cumulative deviation value within the diffusion range; The system calculates the duration of temperature anomaly and the temperature cumulative deviation value within the diffusion range, specifically including: obtaining the historical temperature data of all detection points within the diffusion range; calculating the temperature mean and standard deviation of the historical temperature data in different time periods; determining the normal range of temperature fluctuations based on the temperature mean and standard deviation, and taking the temperature mean plus or minus twice the standard deviation as the upper threshold and lower threshold of the normal range respectively; counting the duration during which the real-time temperature data of the detection points within the diffusion range exceeds the upper threshold or is lower than the lower threshold, and taking the longest duration as the duration of temperature anomaly; calculating the difference between the temperature value exceeding the upper threshold and the upper threshold, or the difference between the temperature value lower than the lower threshold and the lower threshold in the real-time temperature data of the detection points within the diffusion range; taking the integral value of the difference over time as the temperature cumulative deviation value.

[0071] After determining the diffusion range, the system needs to further quantify the duration of temperature anomaly and the cumulative deviation value to evaluate the severity of the anomaly. The duration of temperature anomaly reflects the time span of the abnormal state, while the temperature cumulative deviation value reflects the degree of deviation of the abnormal temperature from the normal range.

[0072] To calculate the duration of temperature anomaly, the system first obtains the historical temperature data of all detection points within the diffusion range and calculates the temperature mean and standard deviation in different time periods. Based on the mean and standard deviation, the system determines the normal range of temperature fluctuations, usually taking the mean plus or minus twice the standard deviation as the upper and lower threshold values. Then, the system counts the duration during which the real-time temperature data of the detection points within the diffusion range exceeds the normal range, and selects the longest duration as the duration of temperature anomaly for the entire diffusion range.

[0073] For the temperature cumulative deviation value, the system calculates the difference between the real-time temperature data of the detection points within the diffusion range and the upper and lower threshold values of the normal range. These differences are accumulated in the time dimension, that is, the difference between the temperature value exceeding the upper threshold and the upper threshold, or the difference between the temperature value lower than the lower threshold and the lower threshold is integrated to obtain the temperature cumulative deviation value. The larger the temperature cumulative deviation value, the more severe the degree of deviation of the temperature anomaly.

[0074] S205. Calculate the harm degree of environmental factors according to the duration of temperature anomaly, the temperature cumulative deviation value and the area of the diffusion range; The system calculates the harm degree of environmental factors based on the duration of temperature anomaly, the cumulative temperature deviation value, and the area of the diffusion range. Specifically, it includes: obtaining the preset reference duration, the preset reference cumulative deviation value, and the preset reference area; dividing the duration of temperature anomaly by the preset reference duration to obtain the time weight coefficient; dividing the cumulative temperature deviation value by the preset reference cumulative deviation value to obtain the temperature weight coefficient; dividing the area of the diffusion range by the preset reference area to obtain the area weight coefficient; taking the sum of the product of the duration of temperature anomaly and the time weight coefficient, the product of the cumulative temperature deviation value and the temperature weight coefficient, and the product of the area of the diffusion range and the area weight coefficient as the value corresponding to the harm degree of environmental factors.

[0075] After obtaining the duration of temperature anomaly, the cumulative temperature deviation value, and the area of the diffusion range, the system needs to comprehensively consider these factors and calculate the harm degree of environmental factors. The harm degree is a quantitative index that reflects the severity of the possible damage caused by temperature anomalies to the environment and facilities.

[0076] The system first obtains the preset reference duration, reference cumulative deviation value, and reference area as the reference standards for calculating the harm degree. Then, the system calculates the ratios of the duration of temperature anomaly, the cumulative temperature deviation value, and the area of the diffusion range to the reference values respectively to obtain the corresponding weight coefficients. Finally, multiply the duration of temperature anomaly, the cumulative temperature deviation value, and the area of the diffusion range by their respective weight coefficients and sum them up to obtain the numerical representation of the harm degree of environmental factors.

[0077] When setting the weight coefficients, the system can assign different weights according to the influence degree of different factors on the harm degree. For example, the duration of temperature anomaly may better reflect the long-term impact of the anomaly than the cumulative temperature deviation value, so a higher weight is given. Similarly, the larger the area of the diffusion range, the wider the spatial range of the anomaly's influence, so a higher weight is also given. The specific setting of the weights can be optimized through empirical estimation or data-driven methods, such as statistical analysis based on historical events or machine learning algorithms.

[0078] S206. When the harm degree exceeds the preset third threshold, set the level of the environmental factor warning information to an emergency warning; when the harm degree is lower than the preset fourth threshold, set the level of the environmental factor warning information to a general warning.

[0079] After calculating the harm degree of environmental factors, the system needs to generate warning information of corresponding levels according to the level of the harm degree. The purpose of the warning information is to remind relevant personnel to take preventive measures and timely dispose of and control the possible impacts caused by temperature anomalies.

[0080] The system pre-sets two harm level thresholds, namely the third threshold and the fourth threshold, which are used to divide the warning levels. When the harm level exceeds the third threshold, it indicates that the impact of the temperature anomaly is very serious and may cause significant damage to the environment and facilities. Therefore, the system sets the level of the warning information as the highest level of emergency warning. An emergency warning means that immediate emergency measures need to be taken to fully respond to and control the anomaly.

[0081] On the contrary, when the harm level is lower than the fourth threshold, it indicates that the impact of the temperature anomaly is relatively small and may only cause minor or local impacts. Therefore, the system sets the level of the warning information as a lower-level general warning. A general warning means that the abnormal situation needs to be closely monitored and appropriate general preventive measures should be taken, but there is no need to activate the emergency response mechanism.

[0082] When setting the thresholds, the system can refer to industry standards, expert experience, or the statistical distribution of historical data. For example, the harm level value at the time of major accidents in history can be used as a reference for the third threshold, and the harm level value when no obvious damage is caused can be used as a reference for the fourth threshold. The specific values of the thresholds can be adjusted according to different application scenarios and risk preferences to balance the sensitivity and operability of the warning.

[0083] In practical applications, a more fine-grained classification of warning levels may be required to meet the management needs in different situations. For this purpose, the system can set multiple thresholds to divide the harm level into more levels, such as "low-level warning", "medium-level warning", and "high-level warning", etc. The system can also introduce a dynamic threshold adjustment mechanism to adaptively adjust the warning thresholds according to changes in environmental conditions or adjustments in management strategies, making the warning information more accurate and effective.

[0084] In addition, the generation and release of warning information also need to consider the information transmission method and the recipients. The system can send the warning information to the relevant responsible persons and disposal personnel in a timely manner through various channels, such as text messages, emails, APP push, etc. At the same time, the system can also automatically trigger corresponding plans and disposal processes according to the level of the warning, such as activating the emergency response team, dispatching rescue resources, etc., to minimize the losses that may be caused by the temperature anomaly.

[0085] In the above embodiment, by obtaining the real-time temperature data of the detection points within the preset detection radius around the abnormal detection point, combined with the shape characteristics of the temperature contour line, the spatial position characteristics of the temperature maximum point and the direction characteristics of the temperature gradient, the diffusion morphology of the temperature anomaly area can be accurately identified. According to the closed loop or band characteristics of the temperature contour line and the temperature gradient direction, the actual temperature anomaly diffusion range can be accurately defined. By calculating the temperature anomaly duration and the temperature cumulative deviation value within the diffusion range, the severity of the temperature anomaly can be quantitatively evaluated. Taking into account multi-dimensional indicators such as duration, cumulative deviation value and diffusion range area, the actual degree of harm of environmental factors can be scientifically calculated. By comparing the degree of harm with the preset threshold, the system can automatically determine the urgency of the warning level, thereby realizing the graded warning of temperature anomalies caused by environmental factors. This multi-dimensional evaluation and graded warning mechanism enables the system to accurately distinguish temperature anomalies of different severity, avoid the problem of excessive or insufficient warning, and help warehouse management personnel take prevention and control measures that are consistent with the actual degree of harm.

[0086] The following describes the system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of the physical device structure of a temperature anomaly monitoring system for a grain storage cable interlayer provided in an embodiment of the present application.

[0087] It should be noted that Figure 3 The structure of the system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0088] like Figure 3 As shown, the system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through a bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0089] The following components are connected to the I / O interface 305: an input section 306 including a camera, an infrared sensor, etc.; an output section 307 including a liquid crystal display (LCD), a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is mounted on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0090] Specifically, according to an embodiment of the present invention, the processes described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 309, and / or installed from the removable medium 311. When the computer program is executed by a central processing unit (CPU) 301, various functions defined in the present invention are executed.

[0091] It should be noted that the computer-readable medium shown in the embodiments of the present invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. In the present invention, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable computer program is carried. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above.

[0092] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. Among them, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above module, program segment, or part of code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0093] As another aspect, the present invention also provides a computer-readable storage medium, which may be included in the system described in the above embodiments; or may exist separately without being assembled into the system. The above storage medium carries one or more computer programs, and when the one or more computer programs are executed by a processor of a system, the system implements the method provided in the above embodiments.

[0094] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0095] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if detecting (the stated condition or event)" can be interpreted as "if determining...", "in response to determining...", "when detecting (the stated condition or event)", or "in response to detecting (the stated condition or event)".

[0096] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid-state drive), etc.

[0097] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by relevant hardware instructed by a computer program. This program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. The foregoing storage medium includes various media that can store program codes, such as ROM, random access memory (RAM), magnetic disks, or optical discs.

Claims

1. A method for monitoring abnormal temperature in a cable interlayer of a grain storage warehouse, characterized in that, Including: Collecting real-time temperature data of multiple detection points through a temperature sensor array arranged in a cable interlayer, and the temperature sensor array is spirally distributed along the cable interlayer; Calculating the temperature gradient value and the temperature change rate between adjacent detection points based on the real-time temperature data; Determining the feature vector of each detection point, and the dimension of the feature vector includes the current temperature value of the detection point, the temperature gradient value with adjacent detection points, the temperature change rate, and the spatial position coordinates of the detection point; Calculating the anomaly score corresponding to each detection point according to the feature vector of each detection point and a temperature anomaly scoring function; when detecting an anomaly detection point whose anomaly score exceeds a preset first threshold, extracting the feature vectors of all detection points within a preset range centered on the anomaly detection point; Calculating the temperature distribution pattern feature within the preset range based on the extracted feature vectors; Performing a matching degree analysis on the temperature distribution pattern feature and the typical temperature distribution patterns caused by grain self-heating and external environmental factors according to a pre-established temperature distribution pattern feature library to obtain the similarity with the typical temperature distribution pattern, and the typical temperature distribution pattern includes a grain self-heating pattern and an external environmental factor pattern; When the similarity with the grain self-heating pattern is greater than a preset second threshold, generating a grain self-heating early warning message; when the similarity with the external environmental factor pattern is greater than the preset second threshold, generating an environmental factor early warning message.

2. The method according to claim 1, wherein The temperature anomaly scoring function is: In the above function, S is the anomaly score, T is the current temperature value of the detection point, T0 is the historical normal temperature reference value, T ref is the reference temperature difference, L is the characteristic length, and is the temperature gradient value, ε is a small positive number, τ is the time scale, and d i is the distance to the adjacent detection point, R is the distance, and T i is the temperature value of the adjacent point, N is the set of adjacent points, and α, λ1, λ2, λ3, β, γ, θ, and η are weight coefficients. is the temperature change rate.

3. The method according to claim 1, wherein The calculating the temperature distribution pattern feature within the preset range based on the extracted feature vectors specifically includes: Establishing a continuous temperature field distribution function according to the spatial position coordinates and temperature data of the anomaly detection point included in the extracted feature vectors; Calculating the gradient vector field of the continuous temperature field distribution function to obtain the temperature change direction and change intensity of each detection point within the preset range; Extracting an isothermal surface in the continuous temperature field distribution function, and determining a temperature contour line set through the intersection line of the isothermal surface and a preset plane; Calculating the shape feature parameters of the temperature contour line set; Analyzing the evolution feature of the continuous temperature field distribution function in the time dimension, and calculating the diffusion rate vector of the temperature field, the expansion direction and expansion speed of the abnormal area based on the evolution feature; Combining the shape feature parameters, the diffusion rate vector, the expansion direction and the expansion speed to form the temperature distribution pattern feature.

4. The method according to claim 3, characterized in that, The calculating the shape feature parameters of the temperature contour line set specifically includes: Calculating the area, perimeter and circularity of each contour line in the temperature contour line set; Extracting the spacing data between adjacent contour lines in the temperature contour line set; Calculating the mean and standard deviation of the spacing data; Counting the number of nested layers of the contour lines in the temperature contour line set; Combining the area, the perimeter, the circularity, the spacing mean, the spacing standard deviation and the number of nested layers to form the shape feature parameters.

5. The method according to claim 1, characterized in that After generating the environmental factor early warning message when the similarity with the external environmental factor pattern is greater than the preset second threshold, the method further includes: Obtain the real-time temperature data of all detection points within a preset detection radius around the abnormal detection point; Calculate the temperature spatial distribution characteristics within the preset detection radius, where the temperature spatial distribution characteristics include the shape characteristics of the isotherm, the spatial position characteristics of the temperature maximum point, and the direction characteristics of the temperature gradient; When the isotherm presents a closed ring and the temperature gradient direction points to the center of the ring, determine the ring-shaped area as the diffusion range; when the isotherm presents a band shape and the temperature gradient direction expands horizontally, determine the band-shaped area as the diffusion range; Calculate the temperature anomaly duration and the temperature cumulative deviation value within the diffusion range; Calculate the environmental factor hazard degree according to the temperature anomaly duration, the temperature cumulative deviation value, and the area of the diffusion range; When the hazard degree exceeds a preset third threshold, set the level of the environmental factor warning information to an emergency warning; When the hazard degree is lower than a preset fourth threshold, set the level of the environmental factor warning information to a general warning, where the preset third threshold is greater than the preset fourth threshold.

6. The method according to claim 5, characterized in that The calculation of the temperature anomaly duration and the temperature cumulative deviation value within the diffusion range specifically includes: Obtain the historical temperature data of all detection points within the diffusion range; Calculate the temperature mean value and standard deviation of the historical temperature data in different time periods; Determine the normal range of temperature fluctuations according to the temperature mean value and the standard deviation, and use the temperature mean value plus or minus twice the standard deviation as the upper threshold and the lower threshold of the normal range respectively; Statistically calculate the continuous duration of the real-time temperature data of the detection points within the diffusion range that exceeds the upper threshold or is lower than the lower threshold, and take the longest continuous duration as the temperature anomaly duration; Calculate the difference between the temperature value of the real-time temperature data of the detection points within the diffusion range that exceeds the upper threshold and the upper threshold, or the difference between the temperature value that is lower than the lower threshold and the lower threshold; Take the integral value of the difference over time as the temperature cumulative deviation value.

7. The method according to claim 5, wherein The calculation of the environmental factor hazard degree according to the temperature anomaly duration, the temperature cumulative deviation value, and the area of the diffusion range specifically includes: Obtain a preset reference duration, a preset reference cumulative deviation value, and a preset reference area; Divide the temperature anomaly duration by the preset reference duration to obtain a time weight coefficient; Divide the temperature cumulative deviation value by the preset reference cumulative deviation value to obtain a temperature weight coefficient; Divide the area of the diffusion range by the preset reference area to obtain an area weight coefficient; Take the sum of the product of the temperature anomaly duration and the time weight coefficient, the product of the temperature cumulative deviation value and the temperature weight coefficient, and the product of the area of the diffusion range and the area weight coefficient as the value corresponding to the environmental factor hazard degree.

8. A temperature anomaly monitoring system for a cable interlayer in a grain storage warehouse, characterized in that, The system includes: One or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the system to execute the method according to any one of claims 1-7.

9. A computer-readable storage medium, comprising instructions, characterized in that, When the instructions are running on the system, cause the system to execute the method according to any one of claims 1-7.

10. A computer program product, characterized in that, When the computer program product is running on the system, cause the system to execute the method according to any one of claims 1-7.

Images