Abnormality detection method and system for temperature sensor of smoke exhaust pipeline in catering industry

Abstract

The invention relates to the technical field of electric data processing, and discloses an anomaly detection method and system for a temperature sensor of a smoke exhaust pipeline in the catering industry, and the system comprises a data collection module, a data processing module, a thermal change standard module, an anomaly detection module and a log management module. The data acquisition module obtains sensor temperature values and constructs a data set; the data processing module judges and counts outliers, and establishes a sensitive data set and a second data set; the thermal change standard module obtains a thermal radiation map through an infrared camera, and a time-pixel value curve is obtained; the anomaly detection module judges the accuracy of the sensor according to the data set and the curve; and the log management module stores data. Abnormity of the temperature sensor can be effectively detected, and accuracy and reliability of temperature monitoring of the smoke exhaust pipeline are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical data processing, and in particular, to an abnormal detection method and system for a temperature sensor of a catering industry smoke exhaust pipe. Background Art

[0002] Due to the abnormal control of the temperature of the oil pan on the cook's stove, the oil pan catches fire. The burning stove fire and high temperature are extremely likely to ignite the oil scale in the smoke exhaust pipe, resulting in the overall fire of the smoke exhaust pipe, and then causing serious secondary disasters. Therefore, doing a good job in the temperature detection of the kitchen smoke exhaust pipe is of great significance for preventing flue fires and the safety of public buildings. However, this field has been blank for a long time. Therefore, researching and developing an abnormal detection method or system for a temperature sensor of a catering industry smoke exhaust pipe is of great significance for accurately discovering abnormal temperature conditions in the flue and timely preventing and disposing of flue fire accidents.

[0003] Traditional temperature monitoring methods rely on a single temperature sensor to detect the temperature change in the smoke exhaust pipe in real time. However, these methods often face the risk of the temperature sensor malfunctioning or being inaccurate, resulting in inaccurate monitoring data. In order to improve the accuracy and reliability of temperature monitoring, especially in a complex working environment, a temperature monitoring solution using a multi-point sensor array has emerged.

[0004] However, existing technologies often lack effective abnormal detection means to timely discover the abnormal state of the temperature sensor, such as sensor failure or deviation.

[0005] Therefore, how to accurately detect and identify the abnormality of the temperature sensor through data processing and intelligent analysis, and then improve the accuracy and reliability of the smoke exhaust pipe temperature monitoring system has become an urgent problem to be solved. Summary of the Invention

[0006] In view of this, the present invention proposes an abnormal detection method and system for a temperature sensor of a catering industry smoke exhaust pipe to solve the problem that there is a lack of effective abnormal detection means for the temperature sensor in the prior art.

[0007] On the one hand, an abnormal detection system for a temperature sensor of a catering industry smoke exhaust pipe proposed by the present invention includes: A data acquisition module, electrically connected to the sensor array. The acquisition module is configured to obtain the temperature values of each temperature sensor in the sensor array, construct a data set of the temperature values, acquisition time, and position coordinates of the corresponding temperature sensor, denoted as the first data set, and the first data set is arranged according to the acquisition time; A data processing module, electrically connected to the data acquisition module, configured to judge and count the outliers in the first dataset, establish a sensitive dataset based on the outliers, and establish a second dataset based on the remaining data in the first dataset; A thermal change standard module, electrically connected to the data processing module, configured to obtain a thermal radiation map of the temperature sensor according to an infrared camera, collect the change relationship between time and pixel value at each temperature sensor in the thermal radiation map, and obtain a time-pixel value curve; An anomaly detection module, electrically connected to the data processing module and the thermal change standard module respectively, configured to judge the accuracy of the temperature sensor according to the sensitive dataset, the second dataset and the time-pixel value curve; A log management module, electrically connected to the data acquisition module, the data processing module, the thermal change standard module and the anomaly detection module respectively, and the log management module is used to store data.

[0008] Further, the judgment steps of the outliers include: Obtain the position coordinates of each temperature sensor in the sensor array, determine the positional relationship of each temperature sensor according to the position coordinates, select each temperature sensor as the center one by one, and determine the radius length according to the thermal diffusion coefficient in the smoke exhaust pipe and the standard deviation of the temperature values between the central temperature sensor and all adjacent temperature sensors at the same acquisition time, form the domain range of the current temperature sensor, extract the temperature sensors within the domain range, and judge whether it is an outlier through the following relationship: ; ; ; ; ; Among them, represents temperature sensor i, that is, the current temperature sensor, represents temperature sensor j, that is, the remaining temperature sensors within the neighborhood range except ; represents the temperature difference between two temperature sensors, is the temperature value of the current temperature sensor, is the temperature value of the remaining sensors; is the standard deviation of the temperature difference, is the number of the remaining sensors; is the temperature increment of the current sensor at time t, is the temperature value of the current temperature sensor at time t, The acquisition period set for the temperature sensor; is the critical value of the temperature difference, is the average value of the temperature difference, is the critical coefficient; is the temperature increment of the remaining temperature sensors at time t; is the proportional threshold; If or is satisfied, the temperature value of the current temperature sensor is determined as an outlier.

[0009] Furthermore, the radius length is obtained through the following relationship: ; wherein, is the radius length, is the thermal diffusivity, is the acquisition period set for the temperature sensor, is the maximum distance between two temperature sensors.

[0010] Furthermore, the proportional threshold is obtained through the following method: Obtain a number of groups of correct historical data of the sensor array, calculate the ratio of the maximum value to the minimum value collected by the temperature sensors in each group of correct historical data, and determine the ratio as the proportional threshold.

[0011] Furthermore, when judging and counting the outliers in the first dataset and establishing a sensitive dataset according to the outliers, it includes: When it is judged that there are outliers, the acquisition time and position coordinates corresponding to the outliers are uniformly input into the sensitive dataset.

[0012] Furthermore, when obtaining the time-pixel value curve, it includes: According to the position coordinates of each temperature sensor, an infrared thermal radiation map is obtained by an infrared camera in each acquisition period, the infrared thermal radiation map is denoised based on Gaussian filtering or wavelet transform, and the pixel value at each temperature sensor is obtained according to the coordinate position; the time-pixel value curve is established according to the acquisition period and the pixel value.

[0013] Furthermore, when judging the accuracy of the temperature sensor according to the sensitive dataset, the second dataset and the time-pixel value curve, it includes: Obtain the time-pixel value curve and the acquisition time and temperature value of each temperature sensor corresponding in the sensitive dataset, normalize the pixel value and the temperature value respectively according to the min-max normalization method to obtain the time-temperature value curve and the time-pixel value correction curve; Calculate the similarity between the time-temperature value curve and the time-pixel value correction curve, compare the similarity with a similarity threshold. When the similarity is greater than or equal to the similarity threshold, it is determined that the current temperature sensor is accurate. When the similarity is less than the similarity threshold, it is determined that the current temperature sensor is abnormal.

[0014] Further, when determining the accuracy of the temperature sensor based on the sensitive data set, the second data set, and the time-pixel value curve, it further includes: Obtain the temperature values and coordinate positions of each temperature sensor in the sensor array at the same time, and the denoised thermal radiation map. According to the pixel values at the corresponding coordinate positions in the thermal radiation map, normalize the temperature values and pixel values respectively to obtain the normalized temperature values and normalized pixel values. Compare the normalized temperature values and normalized pixel values at the same coordinate position. If the comparison result is equal, it is determined that the temperature sensor is accurate. If the comparison result is not equal, it is determined that the temperature sensor is abnormal.

[0015] Further, when calculating the similarity, it is calculated and obtained through the following relationship: After aligning the first temperature value and pixel value in the time-temperature value curve and the time-pixel value correction curve, calculate the ratio of each temperature value and pixel value in turn. The product of the ratios is recorded as the similarity.

[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention uses a method combining a multi-point sensor array and an infrared thermal radiation map for temperature monitoring. Through the analysis of the real-time data of the sensor and the thermal radiation map, it can effectively determine whether there is an abnormality in the temperature sensor. This multi-level and multi-dimensional monitoring method greatly enhances the accuracy of the temperature monitoring system. Especially in a complex kitchen environment, it can timely identify the faults or deviations of the temperature sensor and avoid potential safety hazards caused by sensor failures.

[0017] The present invention can accurately identify the outliers in the sensor data through a scientific outlier detection method, and input the corresponding time and position data into the sensitive data set. This mechanism can effectively help the system identify the temperature sensors that may have faults, and timely take maintenance or replacement measures to ensure the accuracy and stability of the temperature monitoring data.

[0018] Through the thermal radiation map obtained by the infrared camera and the time-pixel value curve based on the pixel value change, the system can dynamically monitor the thermal change of the temperature sensor and analyze the performance change of the sensor in real time. This thermal change standard module provides an important basis for anomaly detection, further improving the accuracy and reaction speed of the detection.

[0019] Through the min-max normalization method and the comparison between the time-temperature value curve and the time-pixel value correction curve, the present invention can accurately judge the accuracy of the temperature sensor. When the similarity reaches the set threshold, the system can confirm that the sensor is accurate; if the similarity standard is not met, it will be determined that the sensor is abnormal, ensuring the reliability of the temperature monitoring results.

[0020] The system is equipped with a log management module, which can record and store data at each link, including the acquisition data of the temperature sensor, the abnormal detection process, and information such as the thermal change curve. In this way, users can comprehensively trace the monitoring process, facilitating historical data analysis and fault diagnosis, and at the same time improving the maintainability of the system.

[0021] The system of the present invention combines multiple modules such as data acquisition, abnormal detection, and log management to form an intelligent temperature monitoring and abnormal detection system. This system can not only automatically complete data processing and abnormal judgment, but also automatically take corresponding measures according to the monitoring results, such as alarming or prompting for maintenance, thus realizing the full automation of the temperature monitoring process and reducing the need for manual intervention.

[0022] The method of the present invention can flexibly adapt to different types of exhaust ducts and complex working environments. Especially in the catering industry, the environmental factors of the exhaust ducts are complex and diverse. Through accurate temperature monitoring and abnormal detection, the system can operate stably under different conditions and meet the special needs of the catering industry.

[0023] On the other hand, an abnormal detection method for a temperature sensor of an exhaust duct in the catering industry proposed by the present invention includes: S1: Obtain the temperature values of each temperature sensor in the sensor array, construct a data set of temperature values, acquisition time, and the position coordinates of the corresponding temperature sensor, denoted as the first data set, and the first data set is arranged according to the acquisition time; S2: Judge and count the outliers in the first data set, establish a sensitive data set according to the outliers, and establish a second data set according to the remaining data in the first data set; S3: Obtain the thermal radiation map of the temperature sensor according to the infrared camera, collect the change relationship between time and pixel value at each temperature sensor in the thermal radiation map, and obtain the time-pixel value curve; S4: Judge the accuracy of the temperature sensor according to the sensitive data set, the second data set, and the time-pixel value curve; S5: Store the first data set, the sensitive data set, and the second data set.

[0024] It can be understood that the abnormal detection method and system for the temperature sensor of the exhaust duct in the catering industry provided by the present application have the same beneficial effects, which will not be elaborated here. Brief Description of the Drawings

[0025] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings: Figure 1 It is an application scenario diagram of an abnormal detection system for a temperature sensor of a catering industry smoke exhaust pipe according to an embodiment of the present invention.

[0026] Figure 2 It is a functional framework diagram of an abnormal detection system for a temperature sensor of a catering industry smoke exhaust pipe provided by an embodiment of the present invention.

[0027] Figure 3 It is a flowchart of an abnormal detection method for a temperature sensor of a catering industry smoke exhaust pipe provided by an embodiment of the present invention.

[0028] In the figure, 11 is the smoke hood synchronous pipe; 12 is the sensor layout area; 21 is the first fire damper; 22 is the second fire damper; 3 is the smoke exhaust fan; 4 is the main property smoke exhaust pipe. Detailed Embodiments

[0029] The exemplary embodiments disclosed in the present application will be described in more detail below with reference to the drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the drawings and in combination with the embodiments.

[0030] The application scenario of the embodiment of the present invention is as Figure 1 shown. The arrows in the figure indicate the direction of flue gas flow. A number of flue gas generation sources in the kitchen first enter the smoke hood synchronous pipe 11. The sensor layout area 12 is provided with a sensor array. The flue gas sequentially passes through the sensor array, the first fire damper 21, the smoke exhaust fan 3 and the second fire damper 22 from the smoke hood synchronous pipe 11 and enters the main property smoke exhaust pipe 4. Among them, the first fire damper 21 and the second fire damper 22 are arranged on both sides of the smoke exhaust fan 3. The first fire damper 21 and the second fire damper 22 are used to perform a closing operation after a fire occurs to achieve the effect of protecting the smoke exhaust fan 3 and preventing the spread of flue gas or fire.

[0031] Referring to Figure 2 shown, the embodiment of the present invention provides an abnormal detection system for a temperature sensor of a catering industry smoke exhaust pipe, including: A data acquisition module, electrically connected to the sensor array. The acquisition module is configured to obtain the temperature values of each temperature sensor in the sensor array, construct a data set of temperature values, acquisition times, and the position coordinates of the corresponding temperature sensors, denoted as the first data set, and the first data set is arranged according to the acquisition time; A data processing module, electrically connected to the data acquisition module. The data processing module is configured to judge and count the outliers in the first data set, establish a sensitive data set based on the outliers, and establish a second data set based on the remaining data in the first data set; A thermal change standard module, electrically connected to the data processing module. The thermal change standard module is configured to obtain the thermal radiation map of the temperature sensor according to the infrared camera, collect the change relationship between time and pixel value at each temperature sensor in the thermal radiation map, and obtain a time-pixel value curve; An anomaly detection module, electrically connected to the data processing module and the thermal change standard module respectively. The anomaly detection module is configured to judge the accuracy of the temperature sensor according to the sensitive data set, the second data set, and the time-pixel value curve; A log management module, electrically connected to the data acquisition module, the data processing module, the thermal change standard module, and the anomaly detection module respectively. The log management module is used to store data.

[0032] It should be noted that the sensor array is a number of temperature sensors with known position coordinates pre-deployed in the smoke exhaust duct, which is used to detect the temperature data of the duct, and each temperature sensor is evenly distributed.

[0033] For the convenience of calculation and processing, all parameters participating in the formula calculation are dimensionless before calculation.

[0034] Specifically, the data acquisition module can obtain the data of the temperature sensors in real time and construct a complete data set (the first data set) based on the acquisition time and the sensor positions, ensuring the timeliness and accuracy of the monitoring data. This enables the system to reflect the temperature changes in the smoke exhaust pipe in real time, facilitating immediate monitoring and maintenance. The data processing module can identify and count the outliers, and then construct a sensitive data set based on the outliers, effectively identifying faulty sensors or abnormal temperature data. By intelligently screening and processing the data, the accuracy of temperature monitoring is ensured, and misjudgments caused by sensor failures or data anomalies are reduced. The thermal change standard module combines an infrared camera to analyze the thermal radiation changes of the temperature sensors through a time-pixel value curve, assisting in judging the accuracy of the sensors. The reliability of the temperature sensors can be verified through additional thermal radiation data, enhancing the comprehensiveness and accuracy of the system's temperature monitoring. The anomaly detection module comprehensively analyzes the sensitive data set, the second data set, and the time-pixel value curve to judge the accuracy of the temperature sensors from multiple dimensions, further improving the accuracy of anomaly detection. The system can intelligently identify and handle potential problems of the sensors, thus avoiding the adverse consequences caused by temperature monitoring errors. The log management module records the detailed information of all data acquisition, processing, analysis, and anomaly detection, providing comprehensive support for later fault tracking, data analysis, and system optimization. The storage and management of data not only improve the traceability of the system but also ensure that the system can be quickly diagnosed and restored in case of failures. This system realizes a fully automated workflow from data acquisition, processing to anomaly detection, reducing the need for manual intervention and improving the monitoring efficiency. Through intelligent data analysis and anomaly recognition, the system can automatically process problems when they occur, enhancing the safety and reliability of operation.

[0035] In some embodiments of the present application, the steps for judging outliers include: Obtain the position coordinates of each temperature sensor in the sensor array, determine the positional relationship of each temperature sensor according to the position coordinates, select each temperature sensor as the center one by one, and determine the radius length according to the thermal diffusion coefficient in the smoke exhaust pipe and the standard deviation of the temperature values between the central temperature sensor and all adjacent temperature sensors at the same acquisition time to form the domain range of the current temperature sensor, extract the temperature sensors within the domain range, and judge whether it is an outlier through the following relationship: ; ; ; ; ; Wherein, represents the temperature sensor i, that is, the current temperature sensor, denotes the temperature sensor j, that is, the remaining temperature sensors within the neighborhood range except The remaining temperature sensors within the neighborhood range except denotes the temperature difference between two temperature sensors, is the temperature value of the current temperature sensor, is the temperature value of the remaining sensors; is the standard deviation of the temperature difference, is the number of remaining sensors; is the temperature increment of the current sensor at time t, is the temperature value of the current temperature sensor at time t, is the acquisition period set for the temperature sensor; is the critical value of the temperature difference, is the average value of the temperature difference, is the critical coefficient; is the temperature increment of the remaining temperature sensors at time t; is the proportional threshold; If or is satisfied, then the temperature value of the current temperature sensor is determined as an outlier.

[0036] Specifically, the positional relationship is how many temperature sensors the current temperature sensor is adjacent to or separated from the other temperature sensors.

[0037] It should be noted that by considering the thermal diffusion coefficient in the smoke exhaust duct and the positional coordinate relationship between sensors, the standard deviation is used to determine the domain range of the current temperature sensor. It can dynamically adjust the judgment radius according to the actual environmental heat conduction characteristics to ensure that the identification of outliers is more in line with the actual physical laws. Compared with the traditional judgment methods based on fixed radius or simple distance, this judgment method based on thermal diffusion is more accurate and can better adapt to the temperature change characteristics in different environments. In the outlier judgment, the method of selecting each temperature sensor as the center one by one is adopted, and it is determined whether it is an outlier according to the temperature difference from the surrounding adjacent sensors. This system does not rely on a static global model, but dynamically adjusts the judgment criteria according to the local environment and changes of each sensor, and has strong adaptability. By considering multiple factors such as temperature difference, temperature increment and standard deviation, and combining the data of adjacent temperature sensors, this judgment method can accurately capture the instantaneous abnormal fluctuations, rather than relying solely on a single data point. This way of integrating multiple statistical features can effectively avoid misjudgments caused by environmental noise or errors of a single sensor, and improves the robustness of outlier identification. In the judgment process, by calculating the proportional threshold and comparing it with the temperature difference, the system can adaptively adjust the sensitivity. This dynamic adjustment mechanism can flexibly adjust the threshold of anomaly detection according to different environments, sensor performances and historical data changes, enhancing the flexibility and accuracy of the system.

[0038] In some embodiments of the present application, the radius length is obtained through the following relationship: ; Wherein, is the radius length, is the thermal diffusion coefficient, is the acquisition period set for the temperature sensor, is the maximum distance between two temperature sensors.

[0039] It should be noted that by introducing the thermal diffusivity into the radius calculation, the judgment range can be dynamically adjusted according to the heat conduction characteristics. The thermal diffusivity takes into account the propagation speed and range of heat in the pipeline, making the judgment process more in line with the actual heat conduction law. This enables the selection of the radius length to not only depend on the distance but also reflect the actual diffusion trend of temperature changes, improving the accuracy of anomaly detection. Combining with the acquisition period of the temperature sensor, the system can automatically adjust the sensitivity of outlier judgment according to the acquisition frequencies and data change periods of different sensors. When the acquisition period is short, rapid-changing anomalies can be more precisely identified. When the acquisition period is long, false judgments caused by short-term fluctuations can be reduced. Through the adaptive adjustment of the acquisition period, the response speed and flexibility of the system are enhanced. Introducing the maximum interval distance as a parameter for radius calculation ensures that even when the physical distance between sensors in the pipeline is large, the radius length can still reasonably cover the relevant area, avoiding the lack of anomaly detection due to too large a sensor interval. By reasonably setting the maximum interval, the comprehensiveness of the detection area can be guaranteed, reducing the risk of missed detection. Considering multiple factors (thermal diffusivity, acquisition period, maximum interval distance) comprehensively, the size of the outlier detection area can be automatically adjusted according to different environments and different sensor configurations. In this way, different environmental conditions and sensor layouts can be adapted, greatly improving the accuracy of anomaly detection and avoiding errors that may be caused by fixed radius judgment.

[0040] In some embodiments of the present application, the proportional threshold is obtained by the following method: Obtain several groups of correct historical data of the sensor array, calculate the ratio of the maximum value to the minimum value collected by the temperature sensor in each group of correct historical data, and determine the ratio as the proportional threshold.

[0041] By analyzing historical data and calculating the ratio of the maximum value to the minimum value in each group of data, a threshold based on actual data can be provided for anomaly detection of temperature sensors. It can reflect the temperature change range of the sensor under normal working conditions, thus providing a practical and feasible reference standard for subsequent anomaly detection. Determining the ratio threshold dynamically according to the actual temperature fluctuations in historical data avoids misjudgments that may be caused by fixed thresholds. Over time, the system can automatically adjust the ratio threshold according to new historical data to ensure that the anomaly detection standard matches the actual working environment and data fluctuations, improving the adaptability and robustness of the system. Traditional anomaly detection methods often rely on manually set thresholds, which may introduce errors due to changes in different environments, sensor types, or working conditions. By automatically calculating the ratio threshold based on historical data, the errors caused by human intervention are reduced, and the accuracy and consistency of anomaly detection are improved. By calculating the ratio of the maximum value and the minimum value, the actual amplitude of temperature change can be captured to determine whether there is an anomaly. This system can effectively identify situations where the temperature fluctuation exceeds a reasonable range, improving the sensitivity and detection accuracy of the system to sudden anomalies. In addition, it can adapt to the temperature fluctuation characteristics under different sensor arrays and different working conditions. When the configuration of the sensor array or the working environment changes, through the calculation of the ratio threshold of historical data, the system can flexibly adjust the detection standard to ensure high accuracy in different situations.

[0042] In some embodiments of the present application, when judging and counting the outliers in the first dataset and establishing a sensitive dataset based on the outliers, it includes: When it is judged that there are outliers, the acquisition time and position coordinates corresponding to the outliers are uniformly input into the sensitive dataset.

[0043] In some embodiments of the present application, when obtaining the time-pixel value curve, it includes: According to the position coordinates of each temperature sensor, an infrared thermal radiation map is obtained by an infrared camera in each acquisition cycle, the infrared thermal radiation map is denoised based on Gaussian filtering or wavelet transform, and the pixel values at each temperature sensor are obtained according to the coordinate positions; a time-pixel value curve is established based on the acquisition cycle and the pixel values.

[0044] It should be noted that by using Gaussian filtering or wavelet transform to denoise the infrared thermal radiation map, environmental noise and interference can be effectively reduced, ensuring that the collected thermal radiation map is clearer and more stable. This denoising process helps to improve the accuracy of subsequent temperature measurement and data analysis, ensuring that the pixel values obtained by the temperature sensor can accurately reflect the actual temperature changes. According to the position coordinates of each temperature sensor, the corresponding pixel values are extracted from the infrared thermal radiation map, enabling the precise association of the temperature sensor with the infrared thermal radiation map. In this way, the data of the temperature sensor can be directly corresponded to the thermal changes in the environment, enhancing the system's spatial perception ability of temperature changes. By combining the acquisition period and pixel values to construct a time-pixel value curve, the system can track and record the temperature data of the temperature sensor over time. This system can capture the dynamic change trend of temperature, thus more effectively identifying abnormal fluctuations or sudden changes in temperature changes, helping to detect potential system failures or abnormal states in a timely manner. Using the combination of infrared thermal radiation maps and pixel values can calibrate and verify the measurement accuracy of the sensor, especially in complex environments or when multiple temperature sensors coexist. Through the association of the temperature sensor position and infrared image data, the limitations of single-sensor data can be effectively compensated, improving the overall accuracy and environmental adaptability of the system. The time-pixel value curve provides a perspective of time series data, allowing the system to perform more complex data analysis, such as trend analysis, anomaly detection, model prediction, etc. By analyzing the patterns of temperature changes, the system can more sensitively identify sudden temperature anomalies and early warn of possible faults or safety issues. Combining the position coordinates of the temperature sensor with the pixel values in the infrared image enables the system to accurately locate the temperature anomaly area in space and time. When a fault or anomaly occurs, the fault can be quickly located through the time-pixel value curve and thermal radiation map, improving the system's fault diagnosis and maintenance efficiency. By combining the infrared thermal radiation map and the pixel value data of the temperature sensor, a visual thermal map or temperature change curve can be generated to intuitively display the system operation status. This visualization effect helps managers quickly understand the dynamic characteristics of temperature changes and make timely decisions.

[0045] In some embodiments of the present application, when judging the accuracy of the temperature sensor according to the sensitive data set, the second data set and the time-pixel value curve, it includes: Obtain the time-pixel value curve and the acquisition time and temperature values corresponding to each temperature sensor in the sensitive data set, and normalize the pixel values and temperature values respectively according to the min-max normalization method to obtain a time-temperature value curve and a time-pixel value correction curve; Calculate the similarity between the time-temperature value curve and the time-pixel value correction curve, compare the similarity with the similarity threshold. When the similarity is greater than or equal to the similarity threshold, it is determined that the current temperature sensor is accurate; when the similarity is less than the similarity threshold, it is determined that the current temperature sensor is abnormal.

[0046] It should be noted that by calculating the similarity between the time-temperature value curve and the time-pixel value correction curve, the accuracy of the temperature sensor can be judged based on the similarity between the two data sets. Using the min-max normalization method to standardize the pixel values and temperature values respectively can eliminate the deviation caused by different data scales or dimensions, making the similarity calculation more objective and accurate. This system can effectively reduce the interference of external factors on the accuracy judgment of the temperature sensor and improve the reliability of the accuracy judgment. By processing the time-pixel values and time-temperature values through min-max normalization, it is ensured that these two data sets are within the same range, avoiding comparison errors between data of different scales. This normalization process helps to improve the consistency of the data, provides more accurate and reliable input for the subsequent similarity calculation, and effectively enhances the detection ability of the system. According to the comparison between the calculated similarity and the similarity threshold, when the similarity is lower than the set threshold, the system can promptly determine that there is an abnormality in the current temperature sensor. This real-time accuracy detection mechanism can quickly identify the problematic sensor, issue an anomaly warning, avoid temperature monitoring failure caused by sensor failure, and improve the warning ability and response speed of the system. By using the method of similarity calculation and threshold comparison, the system can keenly capture subtle temperature change anomalies. When the data of the sensor differs significantly from the data of the infrared thermal radiation map, even small-scale temperature fluctuations can be detected in a timely manner. This not only helps to discover anomalies caused by sensor failure, calibration error, or external interference, but also avoids false negatives and false positives, enhancing the accuracy of detection. Based on similarity judgment and threshold comparison, the system can be dynamically adjusted and optimized. If some temperature sensors have long-term accuracy problems, the system can compensate and optimize by analyzing historical data or re-calibrating strategies to ensure that the sensors are always at a high accuracy level and improve the long-term stability of the entire system. When an abnormality of a certain temperature sensor is detected, the system can record the abnormal information of the sensor through the log management module to help maintenance personnel quickly locate and solve the problem. This system reduces the need for manual intervention, improves the automatic monitoring ability of the system, and makes the system more fault-tolerant and maintainable. In a multi-sensor array, by judging the accuracy of multiple sensors, the coordinated operation of the entire sensor array can be ensured. When it is found that the accuracy of some sensors is low, the system can automatically adjust or reallocate the acquisition tasks to ensure the overall consistency and effectiveness of the data. This not only improves the overall accuracy of the sensors but also guarantees the stability during the long-term operation of the system.

[0047] In some embodiments of the present application, when determining the accuracy of the temperature sensor based on the sensitive data set, the second data set, and the time-pixel value curve, it further includes: Obtain the temperature values and coordinate positions of each temperature sensor in the sensor array at the same time, and the denoised thermal radiation map. Normalize the temperature values and pixel values respectively according to the pixel values at the corresponding coordinate positions in the thermal radiation map to obtain the normalized temperature values and normalized pixel values. Compare the normalized temperature values and normalized pixel values at the same coordinate position. If the comparison result is equal, it is determined that the temperature sensor is accurate; if the comparison result is not equal, it is determined that the temperature sensor is abnormal.

[0048] It should be noted that the normalization process can eliminate the differences in dimensions between the temperature values and pixel values, enabling two data from different sources to be compared on the same scale. By normalizing the temperature values and pixel values, it can ensure that the two have the same weight when compared, thus avoiding biases or errors that may be caused by different data dimensions and ensuring the accuracy of the comparison. Directly compare the normalized temperature values and pixel values. If the two are equal, it is determined to be accurate; if not, it is determined to be abnormal. By simplifying the judgment criteria, the complexity of the judgment process is reduced, making the accuracy detection of the temperature sensor more direct and efficient. It avoids complex algorithms and multiple calculation steps, improving the detection speed. The temperature values are directly related to the pixel values in the thermal radiation map. After normalization, the comparison enables the system to sensitively capture accuracy deviations caused by sensor failures, external environmental impacts, or calibration errors, etc. The system can also respond to slight abnormal changes, enhancing the system's ability to identify sensor accuracy problems. The system can compare the temperature values of the temperature sensor with the corresponding thermal radiation image pixel values in real time and make judgments based on each acquisition cycle. By monitoring and judging the accuracy of the temperature sensor in real time, abnormalities can be detected in a timely manner, thereby reducing data distortion or monitoring errors caused by sensor failures, and improving the response speed and accuracy of the system. Due to the standardization of the comparison data through normalization, the abnormal judgment of the temperature sensor is more objective, reducing false alarms or missed alarms caused by factors such as data fluctuations and environmental changes. This makes the system more stable during long-term operation and reduces the maintenance costs caused by inaccurate alarms. By synchronously comparing the temperature values of the temperature sensor with the pixel values obtained by the infrared camera, the data consistency among multiple sensors can be effectively ensured. When there are accuracy errors in some sensors, the system can discover and make adjustments in real time, ensuring the coordination and data consistency of the overall temperature monitoring system and avoiding the impact of local sensor failures on the accuracy of global data. The system combines the comparison of the temperature sensor and the infrared camera image data, making the system have a higher level of intelligence. The system can automatically perform accuracy detection and abnormal alarm according to the matching situation of temperature and pixel data, thereby reducing manual intervention and operation and maintenance costs, and enhancing the automation ability of the system.

[0049] In some embodiments of the present application, when calculating the similarity, it is obtained through the following relationship: After aligning the first temperature value and pixel value in the time-temperature value curve and the time-pixel value correction curve, calculate the ratio of each temperature value to the pixel value in sequence, and the product of the ratios is recorded as the similarity.

[0050] It should be noted that by calculating the ratio of the temperature value to the pixel value and taking the product, the relationship between the two types of data is quantified into a specific value. The greater the similarity, the higher the accuracy of the temperature sensor. This system effectively avoids the computational complexity brought by using complex distance metrics or other algorithms, making the calculation of similarity more concise, direct, and efficient. The ratio calculation between each temperature value and the corresponding pixel value can delicately capture the subtle changes between the temperature sensor and the thermal radiation image pixel values at different acquisition times. By obtaining the similarity through the product of these ratios, the system can more sensitively detect changes in the sensor accuracy, promptly discover sensor anomalies, and avoid problems caused by data deviation or sensor failures. The similarity calculation uses the method of product of ratios, which can effectively eliminate the influence between different data magnitudes and scales, and avoid errors caused by differences in numerical ranges. For example, the temperature value and pixel value may vary within different ranges. By calculating the ratio and then taking the product, the scale can be unified, thereby reducing the computational error caused by the differences in the data itself. By comparing each data point in the time-temperature value curve and the time-pixel value correction curve, the correlation between the temperature change and the thermal radiation image pixel value change in the time dimension can be effectively captured. The trend changes in the time series data are fully considered, ensuring accurate identification and judgment of dynamic changes. Compared with other similarity calculation methods (such as Euclidean distance, cosine similarity, etc.), the product calculation of ratios is more concise and has a lower computational complexity. Therefore, this system can provide efficient and accurate similarity evaluation without adding excessive computational burden, and is suitable for scenarios requiring real-time or large-scale data processing. Through this product calculation of ratios, the value of similarity can directly reflect the precise matching degree between the temperature sensor and the thermal radiation map of the infrared camera. This system provides a clear quantitative standard for subsequent accuracy judgment, facilitating subsequent decision-making and alarm mechanisms. This system provides a simple and intuitive detection mechanism that can quickly locate and identify temperature sensors with abnormal accuracy. This enables staff to quickly find potential faulty sensors during daily operation and maintenance, reducing the time and cost of fault troubleshooting and improving the maintainability of the system.

[0051] Referring to Figure 3 As shown, the embodiments of the present invention also provide an abnormal detection method for a temperature sensor in a catering industry exhaust pipe, including: S1: Obtain the temperature values of each temperature sensor in the sensor array, construct a data set of temperature values, acquisition times, and the position coordinates of the corresponding temperature sensors, denoted as the first data set, and the first data set is arranged according to the acquisition time; S2: Judge and count the outliers in the first data set, establish a sensitive data set based on the outliers, and establish a second data set based on the remaining data in the first data set; S3: Obtain the thermal radiation map of the temperature sensors according to the infrared camera, collect the change relationship between time and pixel values at each temperature sensor in the thermal radiation map, and obtain a time-pixel value curve; S4: Judge the accuracy of the temperature sensors according to the sensitive data set, the second data set, and the time-pixel value curve; S5: Store the first data set, the sensitive data set, and the second data set.

[0052] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: It is still possible to modify the specific implementation manners of the present invention or make equivalent replacements. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. An abnormal detection system for the temperature sensor of the smoke exhaust pipeline in the catering industry, characterized in that, Including: A data acquisition module, electrically connected to the sensor array. The acquisition module is configured to obtain the temperature values of each temperature sensor in the sensor array, construct a data set of the temperature values, acquisition times, and position coordinates of the corresponding temperature sensors, denoted as the first data set, and the first data set is arranged according to the acquisition time. A data processing module, electrically connected to the data acquisition module. The data processing module is configured to judge and count the outliers in the first data set, establish a sensitive data set according to the outliers, and establish a second data set according to the remaining data in the first data set. A thermal change standard module, electrically connected to the data processing module. The thermal change standard module is configured to obtain a thermal radiation map of the temperature sensors according to an infrared camera, collect the change relationship between time and pixel values at each temperature sensor in the thermal radiation map, and obtain a time-pixel value curve. An anomaly detection module, electrically connected to the data processing module and the thermal change standard module respectively. The anomaly detection module is configured to judge the accuracy of the temperature sensors according to the sensitive data set, the second data set, and the time-pixel value curve. A log management module, electrically connected to the data acquisition module, the data processing module, the thermal change standard module, and the anomaly detection module respectively. The log management module is used to store data.

2. The abnormal detection system of the temperature sensor for the catering industry smoke exhaust pipe according to claim 1, wherein The judgment steps of the outliers include: Obtain the position coordinates of each temperature sensor in the sensor array, determine the position relationship of each temperature sensor according to the position coordinates, select each temperature sensor as the center one by one, and determine the radius length according to the thermal diffusion coefficient in the smoke exhaust pipe and the standard deviation of the temperature values between the central temperature sensor and all adjacent temperature sensors at the same acquisition time, form the domain range of the current temperature sensor, extract the temperature sensors within the domain range, and judge whether it is an outlier through the following relationship: ； ； ； ； ； Among them, represents temperature sensor i, i.e., the current temperature sensor, represents temperature sensor j, i.e., the remaining temperature sensors within the neighborhood range except for represents the temperature difference between two temperature sensors, is the temperature value of the current temperature sensor, is the temperature value of the remaining sensors; is the standard deviation of the temperature difference, is the number of the remaining sensors; is the temperature increment of the current sensor at time t, is the temperature value of the current temperature sensor at time t, is the acquisition period set for the temperature sensor; is the critical value of the temperature difference, is the average value of the temperature difference, is the critical coefficient; is the temperature increment of the remaining temperature sensors at time t; is the proportional threshold; If or is satisfied, the temperature value of the current temperature sensor is determined as an outlier.

3. The abnormal detection system for the temperature sensor of the catering industry smoke exhaust pipe according to claim 2, characterized in that, The radius length is obtained through the following relationship: ； Among them, is the radius length, is the thermal diffusivity, is the acquisition period set by the temperature sensor, is the maximum distance between two temperature sensors.

4. The abnormal detection system of the temperature sensor for the catering industry smoke exhaust pipe according to claim 3, characterized in that, The proportional threshold is obtained through the following method: Obtain several groups of correct historical data of the sensor array, calculate the ratio of the maximum value to the minimum value collected by the temperature sensors in each group of correct historical data, and determine the ratio as the proportional threshold.

5. The abnormal detection system of the temperature sensor for the catering industry smoke exhaust pipe according to claim 4, characterized in that, When judging and counting the outliers in the first data set and establishing a sensitive data set according to the outliers, it includes: When it is judged that there are outliers, input the acquisition time and position coordinates corresponding to the outliers into the sensitive data set uniformly.

6. The abnormal detection system for the temperature sensor of the catering industry smoke exhaust pipe according to claim 5, characterized in that, When obtaining the time-pixel value curve, it includes: According to the position coordinates of each temperature sensor, obtain an infrared thermal radiation map through an infrared camera in each acquisition cycle, perform denoising on the infrared thermal radiation map based on Gaussian filtering or wavelet transform, and obtain the pixel values at each temperature sensor according to the coordinate positions; establish the time-pixel value curve according to the acquisition cycle and the pixel values.

7. The abnormal detection system for the temperature sensor of the catering industry smoke exhaust pipe according to claim 6, characterized in that, When judging the accuracy of the temperature sensors according to the sensitive data set, the second data set, and the time-pixel value curve, it includes: Obtain the time-pixel value curve and the acquisition time and temperature values of each temperature sensor corresponding in the sensitive data set. Normalize the pixel values and temperature values respectively according to the min-max normalization method to obtain the time-temperature value curve and the time-pixel value correction curve; Calculate the similarity between the time-temperature value curve and the time-pixel value correction curve, compare the similarity with the similarity threshold. When the similarity is greater than or equal to the similarity threshold, it is determined that the current temperature sensor is accurate. When the similarity is less than the similarity threshold, it is determined that the current temperature sensor is abnormal.

8. The abnormal detection system for the temperature sensor of the catering industry smoke exhaust pipe according to claim 7, characterized in that, When judging the accuracy of the temperature sensor according to the sensitive data set, the second data set and the time-pixel value curve, it further includes: Obtain the temperature values and coordinate positions of each temperature sensor in the sensor array at the same time and the denoised thermal radiation map. Normalize the temperature values and pixel values respectively according to the pixel values at the corresponding coordinate positions in the thermal radiation map to obtain the normalized temperature values and normalized pixel values. Compare the normalized temperature values and normalized pixel values at the same coordinate position. If the comparison result is equal, it is determined that the temperature sensor is accurate. If the comparison result is not equal, it is determined that the temperature sensor is abnormal.

9. The abnormal detection system of the temperature sensor for the catering industry smoke exhaust duct according to claim 8, characterized in that, When calculating the similarity, it is obtained by calculating through the following relationship: After aligning the first temperature value and pixel value in the time-temperature value curve and the time-pixel value correction curve, calculate the ratio of each temperature value and pixel value in turn. The product of the ratios is recorded as the similarity.

10. An abnormal detection method for the temperature sensor of the smoke exhaust pipe in the catering industry, which is applied to the system described in any one of claims 1-9, and is characterized in that, It includes: S1: Obtain the temperature values of each temperature sensor in the sensor array, construct a data set of temperature values, acquisition time and the position coordinates of the corresponding temperature sensor, denoted as the first data set, and the first data set is arranged according to the acquisition time; S2: Judge and count the outliers in the first data set, establish a sensitive data set according to the outliers, and establish a second data set according to the remaining data in the first data set; S3: Obtain the thermal radiation map of the temperature sensor according to the infrared camera, collect the change relationship between the time and pixel values at each temperature sensor in the thermal radiation map, and obtain the time-pixel value curve; S4: Judge the accuracy of the temperature sensor according to the sensitive data set, the second data set and the time-pixel value curve; S5: Store the first data set, the sensitive data set and the second data set.

Images