Temperature Abnormality Detection Method, Device, Electronic Device and Medium

Abstract

The present disclosure provides a temperature anomaly detection method, apparatus, device, medium and product, relating to the field of computer technologies, specifically to the field of deep learning. The temperature anomaly detection method includes: obtaining temperature data and reference data associated with the temperature; processing the temperature data and the reference data to obtain target feature data, where the target feature data includes at least one of first feature data, second feature data and third feature data, the first feature data is associated with the temperature data, the second feature data is associated with the reference data, and the third feature data is associated with the temperature data and the reference data; predicting the anomaly situation of the temperature based on the temperature data, the reference data and the target feature data.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, specifically to the field of deep learning. More specifically, it relates to a temperature anomaly detection method, apparatus, electronic device, medium, and program product. Background Art

[0002] In some scenarios, it is usually necessary to detect whether the temperature is abnormal. For example, in the thermal power station scenario, it is necessary to detect whether the wall temperature of the boiler is abnormal, so as to take effective measures in time to improve the service life of the boiler. Summary of the Invention

[0003] The present disclosure provides a temperature anomaly detection method, apparatus, electronic device, storage medium, and program product.

[0004] According to one aspect of the present disclosure, there is provided a temperature anomaly detection method, including: obtaining temperature data and reference data associated with the temperature; processing the temperature data and the reference data to obtain target feature data, where the target feature data includes at least one of first feature data, second feature data, and third feature data, the first feature data is associated with the temperature data, the second feature data is associated with the reference data, and the third feature data is associated with both the temperature data and the reference data; predicting the anomaly situation of the temperature based on the temperature data, the reference data, and the target feature data.

[0005] According to another aspect of the present disclosure, there is provided a temperature anomaly detection apparatus, including: an obtaining module, a processing module, and a predicting module. The obtaining module is configured to obtain temperature data and reference data associated with the temperature; the processing module is configured to process the temperature data and the reference data to obtain target feature data, where the target feature data includes at least one of first feature data, second feature data, and third feature data, the first feature data is associated with the temperature data, the second feature data is associated with the reference data, and the third feature data is associated with both the temperature data and the reference data; the predicting module is configured to predict the anomaly situation of the temperature based on the temperature data, the reference data, and the target feature data.

[0006] According to another aspect of the present disclosure, there is provided an electronic device, including: at least one processor and a memory communicatively connected to the at least one processor. Wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above temperature anomaly detection method.

[0007] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the above-described temperature anomaly detection method.

[0008] According to another aspect of the present disclosure, there is provided a computer program product including a computer program which, when executed by a processor, implements the above-described temperature anomaly detection method.

[0009] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0011] Figure 1 Schematically shows the system architecture of a temperature anomaly detection and device according to an embodiment of the present disclosure;

[0012] Figure 2 Schematically shows the flowchart of a temperature anomaly detection method according to an embodiment of the present disclosure;

[0013] Figure 3 Schematically shows the principle diagram of a temperature anomaly detection method according to an embodiment of the present disclosure;

[0014] Figure 4 Schematically shows the principle diagram of a temperature anomaly detection method according to an embodiment of the present disclosure;

[0015] Figure 5 Schematically shows the block diagram of a temperature anomaly detection device according to an embodiment of the present disclosure; and

[0016] Figure 6 Is the block diagram of an electronic device for implementing the embodiments of the present disclosure for performing temperature anomaly detection. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to assist in understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0018] The terms used herein are for describing specific embodiments only and are not intended to limit the present disclosure. The terms "including", "comprising", etc. used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0019] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted to have a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0020] In the case of using expressions such as "at least one of A, B, and C", generally, it should be interpreted according to the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include, but is not limited to, a system having only A, only B, only C, having A and B, having A and C, having B and C, and / or having A, B, and C, etc.).

[0021] Embodiments of the present disclosure provide a temperature anomaly detection method, including: obtaining temperature data and reference data associated with the temperature. Then, processing the temperature data and the reference data to obtain target feature data, where the target feature data includes at least one of first feature data, second feature data, and third feature data, the first feature data is associated with the temperature data, the second feature data is associated with the reference data, and the third feature data is associated with the temperature data and the reference data. Next, based on the temperature data, the reference data, and the target feature data, predicting the abnormal situation of the temperature.

[0022] Figure 1 Schematically shows the system architecture of a temperature anomaly detection and device according to an embodiment of the present disclosure. It should be noted that Figure 1 What is shown is only an example of the system architecture to which the embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments, or scenarios.

[0023] As Figure 1 shown, the system architecture 100 according to this embodiment may include data acquisition devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for a communication link between the data acquisition devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0024] The data acquisition devices 101, 102, and 103 can interact with the server 105 through the network 104 to receive or send messages, etc. The data acquisition devices 101, 102, and 103 include, for example, various types of sensors, such as temperature sensors, pressure sensors, etc.

[0025] The server 105 can be a server that provides various services and can be a cloud server with cloud computing capabilities.

[0026] It should be noted that the temperature anomaly detection method provided by the embodiments of the present disclosure can be executed by the server 105. Correspondingly, the temperature anomaly detection device provided by the embodiments of the present disclosure can be set in the server 105. The temperature anomaly detection method provided by the embodiments of the present disclosure can also be executed by a server or a server cluster different from the server 105 and capable of communicating with the data acquisition devices 101, 102, 103 and / or the server 105. Correspondingly, the temperature anomaly detection device provided by the embodiments of the present disclosure can also be set in a server or a server cluster different from the server 105 and capable of communicating with the data acquisition devices 101, 102, 103 and / or the server 105.

[0027] In one example, the server 105 can obtain temperature data and reference data associated with the temperature from the data acquisition devices 101, 102, 103 through the network 104, and predict the abnormal situation of the temperature based on the temperature data and the reference data associated with the temperature.

[0028] It should be understood that Figure 1 the numbers of the client, network, and server in

[0029] are merely illustrative. According to the implementation requirements, there can be any number of clients, networks, and servers. Figure 1 the system architecture of Figures 2 to 4 to describe the temperature anomaly detection method according to the exemplary embodiments of the present disclosure. The temperature anomaly detection method of the embodiments of the present disclosure can be executed, for example, by Figure 1 the server shown in Figure 1 and the server shown in

[0030] Figure 2 is schematically shown as a flowchart of the temperature anomaly detection method according to an embodiment of the present disclosure.

[0031] As Figure 2 shown, the temperature anomaly detection method 200 of the embodiments of the present disclosure can include, for example, operation S210 to operation S230.

[0032] In operation S210, temperature data and reference data associated with the temperature are obtained.

[0033] In operation S220, the temperature data and the reference data are processed to obtain target feature data.

[0034] In operation S230, based on the temperature data, the reference data, and the target feature data, an abnormal condition of the temperature is predicted.

[0035] Exemplarily, the temperature data and the reference data are, for example, data for a boiler tube wall, and the temperature data and the reference data are collected by a data acquisition device, for example. The data acquisition device includes but is not limited to temperature sensors, pressure sensors, and the like.

[0036] In one example, the reference data includes but is not limited to pressure data, power data, and the like, and to a certain extent, the reference data can characterize whether the temperature of the boiler tube wall is normal.

[0037] Exemplarily, the target feature data includes at least one of first feature data, second feature data, and third feature data. The first feature data is associated with the temperature data, for example, the second feature data is associated with the reference data, and the third feature data is associated with the temperature data and the reference data.

[0038] For example, the first feature data is obtained by processing the temperature data, the second feature data is obtained by processing the reference data, and the third feature data is obtained by processing the temperature data and the reference data.

[0039] Next, the temperature data, the reference data, and the target feature data are processed to obtain a prediction result for the temperature. The prediction result represents, for example, the future temperature of the boiler tube wall or the abnormal condition of the temperature of the boiler tube wall.

[0040] According to an embodiment of the present disclosure, the temperature data and the reference data for the boiler tube wall are processed to obtain various types of target feature data, and then, based on the originally collected temperature data and reference data, and various types of target feature data, an abnormal condition of the temperature is predicted. It can be understood that since the originally collected temperature data and reference data have rich information, and the target feature data has relatively obvious feature information, therefore, predicting the temperature abnormality based on the originally collected data and various types of target feature data improves the accuracy of the temperature abnormality prediction, facilitates taking relevant measures in a timely manner according to the prediction result to protect the boiler, and improves the service life of the boiler.

[0041] Figure 3 Schematically shows a schematic diagram of a temperature abnormality detection method according to an embodiment of the present disclosure.

[0042] As Figure 3As shown, temperature data 311 and reference data 312 for the inner wall of the boiler pipeline are collected by the data acquisition device. The reference data 312 includes, for example, but is not limited to, pressure data and power data.

[0043] The first feature data 321 is obtained by processing the temperature data 311. For example, the temperature data 311 within the first preset time period is processed to obtain the first feature data 321 within the first preset time period. The first feature data 321 includes, for example, the variance of the temperature, the maximum value of the temperature, the minimum value of the temperature, the ratio between the maximum value and the minimum value of the temperature, and so on. Taking the variance of the temperature as an example, the first preset time period can be, for example, 6 hours. For example, the variance of the temperature is statistically calculated with a variance sliding window of 6 hours in length. The first feature data 321 characterizes, for example, the inherent characteristics of the temperature data 311.

[0044] The second feature data 322 is obtained by processing the reference data 312. For example, the reference data 312 within the second preset time period is processed to obtain the second feature data 322 within the second preset time period. The reference data 312 includes, for example, pressure data, and the second feature data 322 includes, for example, the variance of the pressure, the maximum value of the pressure, the minimum value of the pressure, the ratio between the maximum value and the minimum value of the pressure, and so on. Taking the variance of the pressure as an example, the second preset time period can be the same as or different from the first preset time period. The second preset time period can be, for example, 6 hours. For example, the variance of the pressure is statistically calculated with a variance sliding window of 6 hours in length. The second feature data 322 characterizes, for example, the inherent characteristics of the pressure data, and the second feature data 322 can characterize the information of the temperature to a certain extent.

[0045] The third feature data 323 is obtained by processing the temperature data 311 and the reference data 312. The reference data 312 includes, for example, pressure data and power data. For example, the temperature data 311 and the reference data 312 within the third preset time period are processed to obtain the third feature data 323. The third preset time period can be the same as or different from the first preset time period or the second preset time period. The third feature data 323 includes, for example, the ratio between the temperature data and the pressure data, the ratio between the temperature data and the power data, the ratio between the pressure data and the power data, and so on. The third feature data 323 can characterize the information of the temperature to a certain extent.

[0046] Next, the temperature data 311, the reference data 312, the first feature data 321, the second feature data 322, and the third feature data 323 are used as input data 330, and the input data 330 is respectively input into at least one type of prediction model for processing.

[0047] For example, using at least one type of prediction model, process temperature data 311, reference data 312, and target feature data (first feature data 321, second feature data 322, third feature data 323) respectively to obtain at least one type of prediction result corresponding one-to-one to the at least one type of prediction model. Then, based on the at least one type of prediction result, determine the abnormal situation of the temperature.

[0048] Taking the case where the at least one type of prediction model includes three types of prediction models as an example, the first type of prediction model 341 is, for example, a tree model with the ability to extract data changes, the second type of prediction model 342 is, for example, a neural network model with temperature prediction ability, and the third type of prediction model 343 is, for example, a time series model with the ability to extract data pattern information and trend information.

[0049] For example, the first type of prediction model 341 can be an Xgboost ensemble tree model. The Xgboost ensemble tree model is more sensitive to data changes. Therefore, by using the Xgboost ensemble tree model to process the input data 330, sensitive information about the temperature change over time in the input data 330 can be obtained.

[0050] For example, the second type of prediction model 342 can include an Informer neural network model and an LSTNet neural network model. The Informer neural network model is, for example, a new time series model for long-sequence time series prediction. The LSTNet neural network model is also called a long short-term time series network model. The second type of prediction model 342 has temperature prediction ability. Therefore, by using the second type of prediction model 342 to process the input data 330, a prediction result for the temperature can be obtained.

[0051] For example, the third type of prediction model 343 can be a Prophet model. The Prophet model is, for example, a time series model with the ability to extract data pattern information and trend information. Therefore, by using the Prophet model to process the input data 330, the change pattern and change trend of the temperature in the input data 330 can be obtained.

[0052] Process the input data 330 respectively by the Xgboost ensemble tree model, the Informer neural network model, the LSTNet neural network model, and the Prophet model to obtain the corresponding prediction results 351, 352, 353, 354. The prediction results 351, 352, 353, 354, for example, characterize the prediction information of temperature anomalies. Then, comprehensively consider the prediction results 351, 352, 353, 354 to obtain the final abnormal situation 360 of the temperature.

[0053] According to an embodiment of the present disclosure, by processing the originally collected temperature data, reference data, and various types of target feature data through various types of prediction models respectively, various types of prediction results are obtained. Compared with the error caused by prediction using one type of prediction model, by comprehensively considering the prediction results of various types of prediction models to obtain the abnormal temperature situation, the detection accuracy of temperature anomalies is improved.

[0054] Figure 4 Schematically shows the principle diagram of a temperature anomaly detection method according to an embodiment of the present disclosure. Figure 4 The illustrated embodiment is Figure 3 a technical solution obtained based on the illustrated embodiment.

[0055] As Figure 4 shown, by processing the temperature data 411 and the reference data 412, the first feature data 421, the second feature data 422, and the third feature data 423 are obtained. The temperature data 411, the reference data 412, the first feature data 421, the second feature data 422, and the third feature data 423 are used as the input data 430, and the input data 430 is respectively input into the first type of prediction model 441, the second type of prediction model 442, and the third type of prediction model 443.

[0056] For each type of prediction model among the Xgboost ensemble tree model, the Informer neural network model, the LSTNet neural network model, and the Prophet model, each type of prediction model includes multiple models, and the model parameters of the multiple models are different from each other. For example, taking the Xgboost ensemble tree model as an example, the Xgboost ensemble tree model includes, for example, 3 models, and the model parameters of the 3 models are different from each other. Thus, 12 models can be obtained. The input data 430 is respectively input into the 12 models to obtain 12 prediction results 451 corresponding one-to-one to the 12 models.

[0057] Then, determine the number of prediction results representing temperature anomalies among the 12 prediction results 451, and based on the ratio between the number of prediction results and the number of multiple models (12), determine the abnormal temperature situation 460. For example, when the ratio is greater than or equal to 2 / 3, the abnormal result is used as the final prediction result of the abnormal temperature situation 460.

[0058] In an example, when 8 or more of the 12 prediction results 451 represent temperature anomalies, the abnormal result is used as the final prediction result of the abnormal temperature situation 460.

[0059] According to an embodiment of the present disclosure, for each type of prediction model, multiple models are obtained by setting different model parameters, and temperature prediction is performed using each model to obtain prediction results. Then, based on the ratio between the number of prediction results indicating temperature anomalies and the number of models among the multiple prediction results, it is finally determined whether there is a temperature anomaly, thereby making the temperature prediction results more reliable and improving the detection accuracy of temperature anomalies.

[0060] The following will describe the temperature anomaly detection of another example.

[0061] First, temperature data and reference data are collected using sensors. The reference data includes, for example, pressure data and power data. For example, temperature data, pressure data, and power data can be collected for the inner walls of the boiler superheater division screens, the inner wall of the boiler steam drum, the final superheater, the rear division superheater, the superheater division screens, the ink reheater, the radiant reheater, the division screen superheater, etc.

[0062] For the temperature data, parameters of the sensor measurement points are set. For example, the flow turbulence is calculated, and then the wall temperature is calculated based on the Dittus - Boelter equation of convective heat transfer using the temperature difference between the inlet and outlet of the boiler pipeline. The calculated temperature can be multiplied by an energy loss coefficient to obtain the final inner wall temperature of the boiler pipeline. The energy loss coefficient is, for example, an empirical value.

[0063] For the pressure data, a pressure sensor can be used to detect the pressure inside the boiler wall temperature.

[0064] For the power data, the power includes the amount of water turned into steam per hour, and the power data can be obtained based on the steam measurement value inside the boiler.

[0065] After collecting the temperature data, pressure data, and power data, the collected data can be pre - processed. For example, data during the boiler startup period can be deleted because this part of the data is unstable and has a lot of noise. In addition, data with missing, abnormal, or statistical errors can be deleted.

[0066] After pre - processing the data, the temperature data and pressure data can be processed using local window variance to obtain the variance, maximum value, minimum value, and the ratio of the maximum value to the minimum value for the temperature data and pressure data respectively. The local window can be a variance sliding window with a length of 6 hours for statistical analysis of the local variance of the data. If the local temperature variance or pressure variance within a certain period suddenly becomes very large, it indicates a greater possibility of boiler anomalies. For example, there may be a leakage in the inner wall of the boiler pipeline. Therefore, based on the variance, not only can temperature anomalies be predicted, but also the safety of the boiler can be predicted.

[0067] In addition, after preprocessing the data, pairwise ratios between temperature data, pressure data, and power data can also be obtained based on the preprocessed data. From the data analysis results, there is a certain ratio relationship between temperature and pressure, and power. From the perspective of analyzing data characteristics, the ratios usually remain within a specific range. If the temperature of the boiler tube wall is abnormal, the ratios between temperature and pressure, and power usually also fluctuate. Therefore, the abnormal situation of temperature can be determined based on the ratios.

[0068] Among them, the variance, maximum value, minimum value, ratio of the maximum value to the minimum value of temperature data and pressure data, as well as the pairwise ratios between temperature data, pressure data, and power data, can be used as target feature data and input into the prediction model.

[0069] For the preprocessed temperature data, pressure data, and power data, further filtering processing can also be performed. For example, the data can be filtered through wavelet denoising and Kalman filters. The denoised data can be used as the input of the prediction model. The denoised data can, for example, reflect the change trend of the data. Using it as the input of the prediction model can improve the prediction ability of the model.

[0070] In addition, the temperature of the inner wall of the boiler pipe can be detected in real time. For example, for different superheaters, there are certain range limits for the temperature inside the dividing screen. For example, the normal temperature of the high-temperature superheater generally fluctuates around 615 degrees, while the normal temperature of the low-temperature superheater is generally between 457 and 512 degrees. Therefore, temperature curves for different instruments (filters) can be plotted. When the detected temperature deviates from the normal curve by a certain range, it can be preliminarily considered that the temperature is abnormal. The results of detecting temperature anomalies through temperature curves and the model prediction results can be used as comprehensive results for risk assessment of temperature anomalies.

[0071] For each category model among the Xgboost ensemble tree model, Informer neural network model, LSTNet neural network model, and Prophet model, during model training, multiple training samples are required for training. The training samples include, for example, training data and validation data for temperature, pressure, and power. The acquisition time of the validation data is, for example, after the acquisition time of the training data.

[0072] Training data for temperature, pressure, and power, for example, includes: data obtained by preprocessing and filtering temperature data, pressure data, and power data; characteristic data such as the variance, maximum value, minimum value, and the ratio of the maximum value to the minimum value of temperature and pressure; pairwise ratios between temperature data, pressure data, and power data, etc. The collection time of the training data is, for example, the first time, and a prediction result (the prediction result includes, for example, the value of the temperature or whether the temperature is abnormal) at a second time (after the first time) is obtained based on the training data. The prediction result is compared with the verification data to obtain a difference, and the parameters of the model are adjusted backward based on the difference until the obtained prediction result is close to the verification data.

[0073] After the model is trained, when using the model for temperature prediction, data can be input into the model. The input data includes, for example: data obtained by preprocessing and filtering temperature data, pressure data, and power data; characteristic data such as the variance, maximum value, minimum value, and the ratio of the maximum value to the minimum value of temperature and pressure; pairwise ratios between temperature data, pressure data, and power data, etc. The model outputs a future temperature prediction result or a result indicating whether the temperature is abnormal. When the model outputs a future temperature, if the temperature deviates from the normal range, it indicates that the future temperature may be abnormal.

[0074] According to an embodiment of the present disclosure, risk management is performed for the heat absorption of the boiler tube wall, and the reasons for the increase in the tube wall temperature and the severity of its consequences are analyzed. Based on online monitoring, refined in-depth detection, and health status evaluation, it is determined that corresponding measures need to be taken to improve the safety of boiler operation, reduce boiler material loss, and extend the service life of the boiler.

[0075] Figure 5 A block diagram of a temperature anomaly detection device according to an embodiment of the present disclosure is schematically shown.

[0076] As Figure 5 shown, the temperature anomaly detection device 500 according to an embodiment of the present disclosure includes, for example, an acquisition module 510, a processing module 520, and a prediction module 530.

[0077] The acquisition module 510 can be used to acquire temperature data and reference data associated with the temperature. According to an embodiment of the present disclosure, the acquisition module 510 can, for example, perform the operation S210 described above with reference to Figure 2 and will not be elaborated here.

[0078] The processing module 520 can be used to process the temperature data and the reference data to obtain target feature data, where the target feature data includes at least one of the first feature data, the second feature data, and the third feature data. The first feature data is associated with the temperature data, the second feature data is associated with the reference data, and the third feature data is associated with both the temperature data and the reference data. According to an embodiment of the present disclosure, the processing module 520 can, for example, perform the operation S220 described above with reference to Figure 2 which will not be elaborated here.

[0079] The prediction module 530 can be used to predict the abnormal situation of the temperature based on the temperature data, the reference data, and the target feature data. According to an embodiment of the present disclosure, the prediction module 530 can, for example, perform the operation S230 described above with reference to Figure 2 which will not be elaborated here.

[0080] According to an embodiment of the present disclosure, the prediction module 530 includes: a processing sub-module and a determination sub-module. The processing sub-module is used to process the temperature data, the reference data, and the target feature data respectively by using at least one type of prediction model to obtain at least one type of prediction results corresponding one-to-one to the at least one type of prediction model; the determination sub-module is used to determine the abnormal situation of the temperature based on the at least one type of prediction results.

[0081] According to an embodiment of the present disclosure, for each category in the at least one type of prediction model, each category of prediction model includes a plurality of models, and the model parameters of the plurality of models are different from each other; the determination sub-module includes: a first determination unit and a second determination unit. The first determination unit is used to determine the number of prediction results indicating temperature abnormality from the plurality of prediction results corresponding one-to-one to the plurality of models for each category of prediction model; the second determination unit is used to determine the abnormal situation of the temperature based on the ratio between the number of prediction results and the number of the plurality of models.

[0082] According to an embodiment of the present disclosure, the at least one type of prediction model includes: a tree model with the ability to extract data changes, a neural network model with the ability to predict temperature, and a time series model with the ability to extract data regular information and trend information.

[0083] According to an embodiment of the present disclosure, the first feature data includes at least one of the following within the first preset time period: the variance of the temperature, the maximum value of the temperature, the minimum value of the temperature, and the ratio between the maximum value and the minimum value of the temperature.

[0084] According to an embodiment of the present disclosure, the reference data includes pressure data; the second feature data includes at least one of the following within the second preset time period: the variance of the pressure, the maximum value of the pressure, the minimum value of the pressure, and the ratio between the maximum value and the minimum value of the pressure.

[0085] According to an embodiment of the present disclosure, the reference data includes pressure data and power data; the third characteristic data includes at least one of the following: the ratio between temperature data and pressure data, the ratio between temperature data and power data, and the ratio between pressure data and power data.

[0086] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision, and disclosure of the user's personal information involved all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0087] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0088] Figure 6 is a block diagram of an electronic device for implementing the temperature anomaly detection in the embodiments of the present disclosure.

[0089] Figure 6 FIG. shows a schematic block diagram of an exemplary electronic device 600 that can be used to implement the embodiments of the present disclosure. The electronic device 600 is intended to represent various forms of digital computers, such as, for example, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, for example, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0090] As Figure 6 shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0091] A plurality of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0092] The computing unit 601 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 executes the various methods and processes described above, such as the temperature anomaly detection method. For example, in some embodiments, the temperature anomaly detection method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the temperature anomaly detection method described above can be executed. Alternatively, in other embodiments, the computing unit 601 can be configured to execute the temperature anomaly detection method by any other suitable means (e.g., by means of firmware).

[0093] Various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0094] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to the processor or controller of a general-purpose computer, a special-purpose computer, or other programmable temperature anomaly detection devices, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, executed partially on the machine and partially on a remote machine as an independent software package, or executed entirely on a remote machine or server.

[0095] In the context of this disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or 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 foregoing.

[0096] To provide for interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic, speech, or tactile input).

[0097] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0098] A computer system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The client-server relationship is generated by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

[0099] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and no limitations are imposed herein.

[0100] The above specific embodiments do not constitute a limitation on the protection scope of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub - combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the protection scope of this disclosure.

Claims

1. A temperature anomaly detection method, comprising: Obtaining temperature data and reference data associated with the temperature; Processing the temperature data and the reference data to obtain target feature data, wherein the target feature data includes at least one of first feature data, second feature data, and third feature data, the first feature data is associated with the temperature data, the second feature data is associated with the reference data, and the third feature data is associated with the temperature data and the reference data; Using at least one type of prediction model to process the temperature data, the reference data, and the target feature data respectively, to obtain at least one type of prediction result corresponding one-to-one to the at least one type of prediction model, wherein for each category of the at least one type of prediction model, each category of prediction model includes multiple models, and the model parameters of the multiple models are different from each other; For each category of prediction model, determining the number of prediction results indicating temperature anomaly from the multiple prediction results corresponding one-to-one to the multiple models; and Based on the ratio between the number of prediction results and the number of the multiple models, determining the anomaly situation of the temperature.

2. The method according to claim 1, wherein The at least one type of prediction model includes: A tree model with the ability to extract data changes, a neural network model with temperature prediction ability, and a time series model with the ability to extract data pattern information and trend information.

3. The method according to claim 1 or 2, wherein The first feature data includes at least one of the following within a first preset time period: The variance of the temperature, the maximum value of the temperature, the minimum value of the temperature, and the ratio between the maximum value and the minimum value of the temperature.

4. The method according to claim 1 or 2, wherein The reference data includes pressure data; the second feature data includes at least one of the following within a second preset time period: The variance of the pressure, the maximum value of the pressure, the minimum value of the pressure, and the ratio between the maximum value and the minimum value of the pressure.

5. The method according to claim 1 or 2, wherein The reference data includes pressure data and power data; the third feature data includes at least one of the following: The ratio between the temperature data and the pressure data, the ratio between the temperature data and the power data, and the ratio between the pressure data and the power data.

6. A temperature anomaly detection device, comprising: An acquisition module for acquiring temperature data and reference data associated with the temperature; A processing module for processing the temperature data and the reference data to obtain target feature data, wherein the target feature data includes at least one of first feature data, second feature data, and third feature data, the first feature data is associated with the temperature data, the second feature data is associated with the reference data, and the third feature data is associated with the temperature data and the reference data; A processing sub-module for using at least one type of prediction model to process the temperature data, the reference data, and the target feature data respectively, to obtain at least one type of prediction result corresponding one-to-one to the at least one type of prediction model, wherein for each category of the at least one type of prediction model, each category of prediction model includes multiple models, and the model parameters of the multiple models are different from each other; A first determination unit, configured to determine, for each category of prediction models, the number of prediction results characterizing temperature anomalies from a plurality of prediction results corresponding one by one to the plurality of models; and A second determination unit, configured to determine the abnormal condition of the temperature based on the ratio between the number of prediction results and the number of the plurality of models.

7. The apparatus according to claim 6, wherein, The at least one category of prediction models includes: A tree model with the ability to extract data changes, a neural network model with the ability to predict temperature, and a time series model with the ability to extract data regular information and trend information.

8. The device according to claim 6 or 7, wherein, The first feature data includes at least one of the following within a first preset time period: The variance of temperature, the maximum value of temperature, the minimum value of temperature, and the ratio between the maximum value of temperature and the minimum value of temperature.

9. The device according to claim 6 or 7, wherein The reference data includes pressure data; the second feature data includes at least one of the following within a second preset time period: The variance of pressure, the maximum value of pressure, the minimum value of pressure, and the ratio between the maximum value of pressure and the minimum value of pressure.

10. The device according to claim 6 or 7, wherein, The reference data includes pressure data and power data; the third feature data includes at least one of the following: The ratio between the temperature data and the pressure data, the ratio between the temperature data and the power data, and the ratio between the pressure data and the power data.

11. An electronic device, comprising: At least one processor; And A memory communicatively connected to the at least one processor; wherein The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method according to any one of claims 1-5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to execute the method according to any one of claims 1-5.

13. A computer program product, comprising a computer program, where the computer program, when executed by a processor, implements the method according to any one of claims 1-5.

Images