Temperature and humidity monitoring and early warning system for station equipment room

Abstract

The invention discloses a temperature and humidity monitoring and early warning system for a station equipment room, and relates to the technical field of data processing, and the system comprises the steps: collecting the geographical environment features of a target station equipment room, and obtaining a monitoring background feature set according to the collection result; acquiring an abnormal temperature and humidity monitoring information set of a sample station equipment room; obtaining a screening sample abnormal information set; obtaining a screened sample temperature and humidity characteristic group set; fusing the newly added sample exception information set and the screened sample exception information set to obtain a fused sample exception information set; obtaining the monitoring and early warning network layer after training is completed; and the monitoring and early warning network layer is used for carrying out anomaly analysis on the target temperature and humidity monitoring data and carrying out temperature and humidity monitoring and early warning. The technical problems of low temperature and humidity monitoring precision and monitoring result lagging caused by neglect of background features and slow abnormal recognition in the prior art are solved, and the technical effect of improving the accuracy and real-time performance of temperature and humidity monitoring and early warning is achieved.

Description

Technical Field

[0001] The present application relates to the technical field related to data processing, and specifically to a temperature and humidity monitoring and early warning system for a station equipment room. Background Art

[0002] With the rapid development of modern transportation networks, stations and their equipment rooms, as important facilities, undertake a large number of operation and management tasks. In order to ensure the normal operation of equipment and the safety of passengers and staff, environmental monitoring of station equipment rooms has become particularly important, especially the monitoring of temperature and humidity, which is of great significance for the normal operation of equipment and avoiding equipment failures caused by environmental factors. However, traditional temperature and humidity monitoring mostly relies on real-time data acquisition and simple threshold alarm methods of a single sensor. There are still many deficiencies in the recognition and early warning of temperature and humidity anomalies in complex environments. For example, the environmental conditions of station equipment rooms change frequently, and the sensor data is huge and complex. It is difficult to effectively extract important information, especially abnormal temperature and humidity changes and potential hidden dangers, by relying solely on traditional methods; the response to sudden abnormal changes and environmental changes is slow, resulting in untimely early warning; the existing methods ignore the comprehensive analysis of background characteristics, lack of effective modeling and mining of specific environmental factors in station equipment rooms, and different station equipment rooms have different factors such as geography, environment, and usage conditions, resulting in inaccurate early warning.

[0003] Therefore, in the current relevant technologies, there are technical problems such as ignoring background features and slow anomaly recognition, which leads to low temperature and humidity monitoring accuracy and delayed monitoring results. Summary of the invention

[0004] This application solves the technical problems in the prior art of ignoring background features and slow abnormality recognition, which lead to low temperature and humidity monitoring accuracy and delayed monitoring results, by providing a temperature and humidity monitoring and early warning system for the station equipment room. It achieves the technical effect of improving the accuracy and real-time performance of temperature and humidity monitoring and early warning.

[0005] The present application provides a temperature and humidity monitoring and early warning system for station equipment rooms, the system comprising: a monitoring background feature set acquisition module, used to collect geographical environment features of target station equipment rooms, and obtain a monitoring background feature set according to the collection results; an abnormal temperature and humidity monitoring information set acquisition module, used to use the monitoring background feature set as a label, perform frequent item mining on big data, and obtain a sample station equipment room abnormal temperature and humidity monitoring information set; a sample quality verification and screening module, used to use an NLI filter in combination with the monitoring background feature set, perform sample quality verification and screening on the sample station equipment room abnormal temperature and humidity monitoring information set, and obtain a screening sample abnormal information set; a temperature and humidity feature extraction module, used to perform temperature and humidity feature extraction on the screening sample abnormal information set, and obtain a screening sample temperature and humidity feature group set; A semantic difference analysis module is used to perform semantic difference analysis on the temperature and humidity feature group set of the screened samples, and to combine and paraphrase the screened sample abnormal information set according to the analysis results to obtain a newly added sample abnormal information set, and to fuse the newly added sample abnormal information set with the screened sample abnormal information set to obtain a fused sample abnormal information set; a monitoring and early warning network layer acquisition module is used to perform generative adversarial training of the monitoring and early warning network layer based on the fused sample abnormal information set to obtain the trained monitoring and early warning network layer; a temperature and humidity monitoring and early warning module is used to monitor the temperature and humidity of the equipment room of the target station using a sensor array to obtain target temperature and humidity monitoring data, and to perform abnormal analysis on the target temperature and humidity monitoring data using the monitoring and early warning network layer, and to perform temperature and humidity monitoring and early warning according to the analysis results.

[0006] In a possible implementation, the NLI filter is combined with the monitoring background feature set to perform sample quality verification and screening on the abnormal temperature and humidity monitoring information set of the sample station equipment room to obtain a screened sample abnormal information set, and the following processing is performed: based on the monitoring background feature set, hypothesis data and data labels are generated to obtain a hypothesis data set and a data label set, wherein the data labels include contradiction, implication and neutrality, and each hypothesis data corresponds to a data label; the NLI recognizer built based on the BERT model is trained using the hypothesis data set and the data label set until the training converges to obtain a trained NLI filter; the monitoring background feature set and the abnormal temperature and humidity monitoring information set of the sample station equipment room are input into the NLI filter to obtain a sample data label set; based on the sample data label set, the sample station equipment room abnormal temperature and humidity monitoring information set is sample quality verified and screened to obtain a screened sample abnormal information set.

[0007] In a possible implementation, the sample station equipment room abnormal temperature and humidity monitoring information set is subjected to sample quality verification and screening based on the sample data label set to obtain a screened sample abnormality information set, and the following processing is also performed: when the sample data label in the sample data label set is implicit, the corresponding sample station equipment room abnormal temperature and humidity monitoring information is added to the screened sample abnormality information set; when the sample data label in the sample data label set is contradictory, the corresponding sample station equipment room abnormal temperature and humidity monitoring information is eliminated; when the sample data label in the sample data label set is neutral, it is sent to the sample quality verification personnel for manual verification, and when the manual verification passes, the corresponding sample station equipment room abnormal temperature and humidity monitoring information is added to the screened sample abnormality information set.

[0008] In a possible implementation, a semantic difference analysis is performed on the screening sample temperature and humidity feature group set, and the screening sample abnormality information set is combined and paraphrased according to the analysis result to obtain a newly added sample abnormality information set, and the following processing is also performed: the semantic difference between any one screening sample temperature and humidity feature group in the screening sample temperature and humidity feature group set and the remaining screening sample temperature and humidity feature groups is calculated to obtain a screening sample temperature and humidity feature group semantic difference set; with a preset semantic difference set as a constraint, the screening sample information corresponding to the semantic difference of the screening sample temperature and humidity feature group in the screening sample temperature and humidity feature group semantic difference set that is lower than the preset semantic difference set is used as a newly added template to obtain a newly added template set; the newly added template set is combined and paraphrased to obtain the newly added sample abnormality information set.

[0009] In a possible implementation, the newly added template set is combined and paraphrased to obtain the newly added sample abnormality information set, and the following processing is also performed: the newly added template set is randomly combined in a preset combination method to obtain a newly added combined sample abnormality information set, wherein the preset combination method is to perform information cross-talk between any one newly added template and at least two newly added templates; keywords of the newly added template set are traversed and extracted to obtain a newly added template keyword group set, wherein each new template keyword group corresponds to a new template; the newly added template keyword group set is randomly converted to synonyms, and the newly added template set is integrated according to the conversion result to obtain a newly added paraphrased sample abnormality information set; the newly added combined sample abnormality information set and the newly added paraphrased sample abnormality information set are used as the newly added sample abnormality information set.

[0010] In a possible implementation, generative adversarial training of the monitoring and early warning network layer is performed based on the fused sample anomaly information set to obtain the trained monitoring and early warning network layer, and the following processing is also performed: the fused sample anomaly information set is divided into a training set and a verification set according to a preset ratio; an initial monitoring and early warning network layer is constructed based on the training set; the initial monitoring and early warning network layer is verified based on the verification set, and if the verification passes, the trained monitoring and early warning network layer is obtained.

[0011] In a possible implementation, the monitoring and early warning network layer that has been trained is obtained, and the following processing is also performed: the training set is traversed to extract feature vectors, and the extraction results are averaged to obtain concentrated feature vectors; a random noise vector is introduced, and interference samples are generated in combination with the concentrated feature vector input into the generator to obtain an interference sample set; the discriminator is trained using the training set and the interference sample set to obtain a discrimination result, and a discrimination loss coefficient is obtained based on the discrimination result; the network parameters of the discriminator and the generator are iteratively updated using the discrimination loss coefficient until a preset number of iterations is met, and the generator and the discriminator that have completed the network parameter update are combined to obtain an initial monitoring and early warning network layer that has completed initial training.

[0012] In a possible implementation, temperature and humidity features are extracted from the screening sample abnormal information set to obtain a screening sample temperature and humidity feature group set, and the following processing is also performed: a feature extraction network layer is pre-built based on a convolutional neural network; and feature analysis is performed on the screening sample abnormal information set using the feature extraction network layer to obtain the sample temperature and humidity feature group set.

[0013] The temperature and humidity monitoring and early warning system for station equipment rooms proposed in this application is intended to collect the geographical environmental characteristics of the target station equipment room, obtain a monitoring background feature set based on the collection results; obtain a sample station equipment room abnormal temperature and humidity monitoring information set; obtain a screening sample abnormal information set; obtain a screening sample temperature and humidity feature group set; fuse the newly added sample abnormal information set with the screening sample abnormal information set to obtain a fused sample abnormal information set; obtain the trained monitoring and early warning network layer; use the monitoring and early warning network layer to perform abnormal analysis on the target temperature and humidity monitoring data, and perform temperature and humidity monitoring and early warning. This solves the technical problems existing in the prior art of ignoring background features and slow abnormal recognition, which in turn leads to low temperature and humidity monitoring accuracy and delayed monitoring results, and achieves the technical effect of improving the accuracy and real-time performance of temperature and humidity monitoring and early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A schematic diagram of the structure of a temperature and humidity monitoring and early warning system for a station equipment room provided in an embodiment of the present application; Figure 2 A schematic diagram of the execution process of the sample quality verification and screening module in the temperature and humidity monitoring and early warning system for the station equipment room provided in an embodiment of the present application.

[0016] Explanation of the accompanying drawings: monitoring background feature set acquisition module 10, abnormal temperature and humidity monitoring information set acquisition module 20, sample quality verification and screening module 30, temperature and humidity feature extraction module 40, semantic difference analysis module 50, monitoring and early warning network layer acquisition module 60, temperature and humidity monitoring and early warning module 70. DETAILED DESCRIPTION

[0017] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0018] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0019] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0020] The embodiment of the present application provides a temperature and humidity monitoring and early warning system for a station equipment room, such as Figure 1 As shown, the system comprises: The monitoring background feature set acquisition module 10 is used to collect geographical environment features of the target station equipment room and obtain the monitoring background feature set according to the collection results.

[0021] Preferably, collecting the geographic environmental characteristics of the target station equipment room refers to obtaining the geographic and environmental data of the target station equipment room and establishing a monitoring background feature set. Specifically, the specific geographic information of the target station equipment room is collected, usually including the geographical location, such as the specific location of the station, the geographical area (for example: city, terrain, climate zone, etc.); building structure, the structure of the building where the equipment room is located, the floor, the degree of isolation, the orientation of the room, etc.; the surrounding environment, the surrounding climate conditions (such as temperate, tropical climate, humidity, etc.), natural environment (such as wind speed, precipitation, etc.) and passenger flow (station passenger flow density), etc.; then based on the collected geographic and environmental characteristics, they are integrated to form a monitoring background feature set, including environmental temperature and humidity characteristics, and may also include equipment characteristics in the room (such as air conditioning, ventilation equipment, power equipment, etc. The operating status, power consumption, etc.), thereby obtaining an environmental feature database as the basis for the monitoring system to analyze temperature and humidity changes and identify anomalies.

[0022] The abnormal temperature and humidity monitoring information set acquisition module 20 is used to perform frequent item mining on big data using the monitoring background feature set as a label to obtain the abnormal temperature and humidity monitoring information set of the equipment room of the sample station.

[0023] Preferably, in the temperature and humidity monitoring and early warning system, background features are used as markers, and frequent item mining technology is used to extract abnormal temperature and humidity data samples from large-scale monitoring data. Specifically, the monitoring background feature set is used as a comparison label to provide a standardized environmental background for subsequent data analysis. For example, under different environmental conditions, the same temperature and humidity may have different normal ranges. By combining the collected monitoring data with these background features, the data can be classified and labeled, and then frequent item mining can be performed on the big data. Frequent item mining is a technology in data mining, which is usually used to extract items or patterns that often appear at the same time from a large amount of data, that is, by analyzing the temperature and humidity monitoring values ​​in the big data, it is possible to identify which temperature and humidity change patterns are in the equipment room of the sample station. For example, a certain temperature and humidity value may appear frequently at a specific time and geographical environment. By comparing with the background feature set, those temperature and humidity combinations that should not appear frequently under normal circumstances are mined to form an abnormal temperature and humidity monitoring information set, which represents the temperature and humidity conditions that may indicate equipment failure, environmental abnormalities or improper equipment operation. Moreover, these abnormal monitoring information come from different station equipment rooms, representing the abnormal conditions that may occur under different environmental conditions in each equipment room. The abnormal temperature and humidity monitoring information set contains all abnormal temperature and humidity data obtained based on data mining technology. These abnormal information are used to determine whether there are potential failures or safety hazards in the equipment room.

[0024] The sample quality verification and screening module 30 is used to use the NLI filter in combination with the monitoring background feature set to perform sample quality verification and screening on the abnormal temperature and humidity monitoring information set of the sample station equipment room to obtain a screened sample abnormal information set.

[0025] Preferably, by using NLI (Non-Linear Integration) filter, combined with the extracted monitoring background feature set, the abnormal temperature and humidity data mined from the big data are quality verified and screened to obtain a high-quality abnormal information set, wherein the NLI filter is a nonlinear integration technology, which is usually used for the fusion and screening of multiple data sources, and can verify and reduce the quality of the data, filter out unqualified, abnormal or irrelevant samples, and the NLI filter can handle nonlinear data relationships, especially for the changes in temperature and humidity data in complex environments. The NLI filter can screen the data more accurately based on nonlinear methods. Through the NLI filter, data from different sources (such as temperature and humidity data, equipment room background features, historical data, etc.) can be combined to comprehensively evaluate the reliability of abnormal data, thereby improving the accuracy of screening. Specifically, in the screening process of abnormal data, the NLI filter does not only work in isolation, but will be combined with the monitoring background feature set for data verification. Guided by the background features, the NLI filter can more effectively distinguish which temperature and humidity anomalies are real system problems and which are invalid anomalies caused by environmental differences or data collection errors, and then determine which temperature and humidity data in a specific room are reasonable fluctuations and which are potential anomalies.

[0026] Preferably, after obtaining a large number of abnormal temperature and humidity monitoring information sets, the NLI filter and the background feature set are used to screen these data together to ensure that only high-quality abnormal samples are retained. The specific screening may include noise filtering to remove erroneous data caused by data transmission errors, equipment failures or other external factors to avoid these invalid data from affecting subsequent analysis; the NLI filter can screen out abnormal data that are truly warning by comparing with the background feature set. For data that is highly inconsistent with background conditions (for example, temperature and humidity exceed the normal range or fluctuate frequently), the NLI filter will judge it as abnormal and retain it in the screening set; finally, a screening sample abnormal information set is obtained, which includes temperature and humidity abnormal information that has been screened from a large amount of monitoring data, verified for quality, and has real warning significance. The abnormal data of the screening sample abnormal information set is of high quality and reliability, and the abnormal data of each station equipment room will be screened according to its specific environmental background to ensure the personalization and pertinence of the data and improve the accuracy of temperature and humidity monitoring.

[0027] The temperature and humidity feature extraction module 40 is used to extract the temperature and humidity features of the screening sample abnormal information set to obtain a screening sample temperature and humidity feature group set.

[0028] Preferably, important features related to temperature and humidity are extracted from the screening sample abnormal information set to form a set containing temperature and humidity features, that is, the screening sample temperature and humidity feature group set. Specifically, the temperature and humidity feature extraction is to identify and extract key temperature and humidity data features from the screened abnormal samples to convert the original temperature and humidity data into effective features that can be used for analysis and modeling. The extracted temperature and humidity features may include average temperature and humidity (average temperature and humidity over a period of time), fluctuation range (the fluctuation range or standard deviation of temperature and humidity data, reflecting the severity of temperature and humidity changes), peak and valley values ​​(identifying temperature and humidity extremes in the data), change rate (rate of temperature and humidity change), time window features (temperature and humidity data are divided into different time windows, such as hours, days, and weeks) and trend features (based on time series data, extract the long-term trend of temperature and humidity and determine its rising or falling direction). These features are integrated into a screening sample temperature and humidity feature group set, which contains the key temperature and humidity features corresponding to all screened abnormal data samples, wherein each screening sample temperature and humidity feature group set includes a temperature feature and a humidity feature, such as high temperature and high humidity, low temperature and high humidity, etc. Through characterized temperature and humidity data, the model can more accurately identify potential anomalies and failures and provide accurate early warnings.

[0029] The semantic difference analysis module 50 is used to perform semantic difference analysis on the screened sample temperature and humidity feature group set, and to combine and paraphrase the screened sample abnormality information set according to the analysis result to obtain a newly added sample abnormality information set, and to fuse the newly added sample abnormality information set with the screened sample abnormality information set to obtain a fused sample abnormality information set.

[0030] Preferably, semantic difference analysis, integration, retelling and optimization are performed on different temperature and humidity features of the screened sample temperature and humidity feature group set to form a fused abnormal information set, that is, a fused sample abnormal information set, which is used to improve the accuracy and comprehensiveness of the monitoring system. Specifically, semantic difference analysis explores the differences between different samples from the semantic level of the data. There may be some minor differences in the data, but these differences often represent different equipment states, environmental changes or potential problems. The difference at the semantic level means that between different temperature and humidity features, there may be some changes that have substantial effects, while some differences may be noise or external environmental interference. For example, a faster rate of temperature change may indicate equipment failure, while a slight temperature fluctuation may be just a normal change in environmental factors. Through semantic difference analysis, the essential differences in temperature and humidity changes between different samples can be identified and distinguished, further improving the accuracy of abnormality identification.

[0031] Preferably, after completing the semantic difference analysis, the abnormal information set of the screened samples is combined and paraphrased according to the analysis results, that is, new abnormal samples are synthesized according to the analysis results of different samples, so as to more comprehensively identify potential problems or faults. Specifically, the key features or abnormal patterns of multiple abnormal samples are combined to generate new samples. For example, if multiple samples have similar abnormalities in certain time periods (such as a sudden increase in temperature and a large change in humidity), these samples are merged into a more representative abnormal pattern, and then the originally scattered abnormal information is converted into a structured and easier to understand abnormal description. For example, the original large changes in temperature and humidity are converted into a more representative abnormal pattern. As the equipment may have potential failures such as overheating or excessive humidity, a new sample abnormal information set is obtained, which is a new abnormal pattern or sample formed through difference analysis and combination on the basis of the original screened samples. It can better reflect the actual changes and potential problems in the equipment environment, and is more representative and accurate than the original sample set. Finally, the new sample abnormal information set is fused with the screened sample abnormal information set to generate a complete abnormal data set containing multiple abnormal patterns and covering different equipment environments and operating states, that is, a fused sample abnormal information set, so as to improve the accuracy of abnormality detection, increase the ability to identify multiple potential problems, and improve the accuracy and timeliness of early warning.

[0032] The monitoring and early warning network layer acquisition module 60 is used to perform generative adversarial training of the monitoring and early warning network layer based on the fused sample abnormal information set to obtain the trained monitoring and early warning network layer.

[0033] Preferably, generative adversarial training of the monitoring and early warning network layer is performed based on the fused sample abnormal information set, wherein a generative adversarial network (GAN) is a deep learning model that generates high-quality data through adversarial training (adversarial learning), including a generator and a discriminator. The generator generates samples that are as close to the real data as possible based on the input random noise or existing data, that is, it generates similar abnormal temperature and humidity data based on the characteristics of the fused samples to simulate potential abnormal patterns. The discriminator is used to distinguish whether the input data is real (that is, from actual monitoring data) or false data generated by the generator, that is, to determine whether a certain temperature and humidity data belongs to an abnormal pattern or is false data generated by the system; the training process of the generative adversarial network is an adversarial training process of the generator and the discriminator. The generator continuously improves the quality of the generated data, and the discriminator continuously improves the ability to identify the generated data. Finally, the generator can generate samples that are very close to the real abnormal data, and the discriminator can accurately judge the authenticity of the data.

[0034] Preferably, the obtained fusion sample abnormal information set is used as training data and input into the GAN model. The generator will try to generate new samples that look similar to the real abnormal temperature and humidity data based on these abnormal data. The discriminator divides the input data into two categories: "real" or "false". The goal is to correctly identify whether the data is real monitoring data or false data generated by the generator. Through adversarial training, the discriminator continuously improves the accuracy of recognition. The goal of the generator is to make the discriminator unable to distinguish between the generated data and the real data, while the goal of the discriminator is to identify the false data as much as possible. Finally, through multiple rounds of adversarial training, the abnormal data generated by the generator will be more real, and the discriminator will become more accurate, thereby obtaining a monitoring and early warning network layer, which is used to analyze temperature and humidity data and predict whether there is anomaly in real time, and can provide accurate anomaly detection and early warning.

[0035] The temperature and humidity monitoring and early warning module 70 is used to use the sensor array to monitor the temperature and humidity of the target station equipment room, obtain target temperature and humidity monitoring data, and use the monitoring and early warning network layer to perform abnormal analysis on the target temperature and humidity monitoring data, and perform temperature and humidity monitoring and early warning according to the analysis results.

[0036] Preferably, in the target station equipment room, temperature and humidity data are collected in real time through a sensor array, and these data are analyzed through a trained monitoring and early warning network layer, so as to identify potential temperature and humidity anomalies in real time and issue early warnings. Specifically, the sensor array is composed of a plurality of temperature and humidity sensors, which are used to monitor the temperature and humidity changes in the target station equipment room in real time. Through the sensor array, temperature and humidity data can be obtained at different room locations or at different heights (such as the ground and the ceiling), and the temperature and humidity data at various locations in the room, i.e., the target temperature and humidity monitoring data, can be obtained more comprehensively and accurately, thereby improving the coverage and accuracy of monitoring. Then, the monitoring and early warning network layer is used to perform abnormal analysis on the target temperature and humidity monitoring data, i.e., to determine whether these data exceed the normal range or whether they show abnormal patterns. , including judging temperature and humidity exceeding the standard, sudden changes (for example, the temperature rises sharply within a few minutes), and continuous trends (long-term abnormal changes in temperature and humidity) to identify any abnormal temperature and humidity phenomena that may affect the normal operation of the equipment or cause safety hazards. Finally, temperature and humidity monitoring and early warning are carried out based on the analysis results. For example, when temperature and humidity abnormalities are detected, early warning notifications are sent to management personnel through various means (such as text messages, emails, visual interfaces, etc.); abnormal reports are generated to record the time, location, temperature and humidity data of the abnormality in detail to help staff analyze the cause of the fault; linked with the station's automated control system (such as air conditioning, ventilation equipment, etc.) to automatically adjust the temperature and humidity to avoid overheating or overhumidification of the equipment; ensure that the environment of the equipment room is adjusted in time to avoid equipment failure or other safety problems due to abnormal temperature and humidity.

[0037] The temperature and humidity monitoring and early warning system for the equipment room of a station according to an embodiment of the present invention is used to solve the technical problems existing in the prior art of ignoring background features and slow abnormal recognition, which leads to low temperature and humidity monitoring accuracy and delayed monitoring results, and achieves the technical effect of improving the accuracy and real-time performance of temperature and humidity monitoring and early warning. The temperature and humidity monitoring and early warning system for the equipment room of a station includes: a monitoring background feature set acquisition module 10, an abnormal temperature and humidity monitoring information set acquisition module 20, a sample quality verification and screening module 30, a temperature and humidity feature extraction module 40, a semantic difference analysis module 50, a monitoring and early warning network layer acquisition module 60, and a temperature and humidity monitoring and early warning module 70.

[0038] The specific configuration of the sample quality verification and screening module 30 will be described in detail below. Figure 2 As shown, the sample quality verification and screening module 30 may further include: generating hypothetical data and data labels based on the monitoring background feature set to obtain a hypothetical data set and a data label set, wherein the data labels include contradiction, implication and neutrality, and each hypothetical data corresponds to a data label; using the hypothetical data set and the data label set to train the NLI recognizer built based on the BERT model until the training converges to obtain a trained NLI filter; inputting the monitoring background feature set and the sample station equipment room abnormal temperature and humidity monitoring information set into the NLI filter to obtain a sample data label set; performing sample quality verification and screening on the sample station equipment room abnormal temperature and humidity monitoring information set based on the sample data label set to obtain a screened sample abnormal information set.

[0039] Preferably, some possible temperature and humidity data and hypothetical data are generated according to the background characteristics. These data do not necessarily represent the monitoring data in the real environment, but are used as part of the training data. Each hypothetical data will be marked with a data label, representing the relationship between the data and the target data, such as contradiction, neutrality, implication, etc., and then the hypothetical data set and the data label set are used to train the NLI recognizer built on the BERT model, wherein BERT (Bidirectional Encoder Representations from Transformers) is a pre-trained language model based on Transformer, which is usually used for natural language processing tasks. It can understand the contextual information in the text and judge the relationship between different sentences, that is, the BERT model is used to understand the relationship between the hypothetical data and the real data, and judge whether they have a contradictory, implication or neutral relationship. Through a large amount of hypothetical data and data labels, the model will learn how to judge whether the temperature and humidity monitoring data has the above three relationships. The training process continues until the model can accurately classify when processing data, and finally obtains a trained NLI filter.

[0040] Preferably, after training is completed, the NLI filter is used to analyze the actual sample station equipment room abnormal temperature and humidity monitoring information set. Specifically, the monitoring background feature set and the abnormal monitoring information set are input into the trained NLI filter. The NLI filter will generate a data label for each input abnormal monitoring data sample. The label indicates whether the data is abnormal and the nature of the abnormality (contradiction, implication or neutrality), which helps to distinguish the abnormalities in the data from normal data; then, sample quality verification and screening are performed based on the sample data label set. The sample data is screened according to the data label set to determine which abnormal data is reliable and which data needs to be excluded, that is, those samples marked as contradictory or implicit are selected as high-quality abnormal data, and the data marked as neutral are excluded. Finally, after screening and quality verification by the NLI filter, a screened sample abnormal information set is obtained, which has high quality and reliability and can be used for subsequent analysis, training or real-time monitoring, thereby improving the accuracy of abnormality identification and early warning effect.

[0041] The specific configuration of the sample quality verification and screening module 30 will be described in detail below. The sample quality verification and screening module 30 may further include: when the sample data label in the sample data label set is implied, the corresponding abnormal temperature and humidity monitoring information of the equipment room of the sample station is added into the screening sample abnormal information set; when the sample data label in the sample data label set is contradictory, the corresponding abnormal temperature and humidity monitoring information of the equipment room of the sample station is eliminated; when the sample data label in the sample data label set is neutral, it is sent to the sample quality verification personnel for manual verification, and when the manual verification passes, the corresponding abnormal temperature and humidity monitoring information of the equipment room of the sample station is added into the screening sample abnormal information set.

[0042] Preferably, when the sample data label is implied, it means that the relationship between the abnormal data and the monitoring background feature set is in line with expectations, that is, the abnormal changes in the data may occur under known environmental conditions, and these changes are reasonable and possible. The data sample can be regarded as valid abnormal information and should be retained, and the data is added to the screening sample abnormal information set; when the sample data label is contradictory, it means that there is an obvious conflict or inconsistency between the abnormal data and the background feature set, which usually indicates that the data sample does not conform to the expected abnormal pattern, or is caused by erroneous equipment monitoring, data noise or other external interference. Since samples with "contradictory" labels may be inaccurate or do not represent real abnormalities, these data samples will be eliminated to maintain the high quality of the data set; when the sample data label is neutral, it means that there is an obvious conflict or inconsistency between the abnormal data and the background feature set. It indicates that the data sample cannot be clearly judged as abnormal or normal under the current analysis model. Its relationship with the background feature set neither constitutes an obvious abnormality nor fully conforms to the known abnormal pattern. It is in a fuzzy state and cannot be judged as valid abnormal data simply by the model. These data are sent to sample quality verification personnel for manual verification, that is, manual analysis is performed on the basis of these data samples to determine whether they are valid abnormal data, such as checking whether there are special factors in the monitoring environment that cause these data samples to be unclear; further verify whether the data is reasonable based on the specific temperature and humidity change pattern and equipment operation status; if the manual verification personnel confirm that the data is valid abnormal information, it is added to the screening sample abnormal information set to ensure the quality and accuracy of the final abnormal information set, so as to improve the accuracy and reliability of the monitoring and early warning system.

[0043] The specific configuration of the semantic difference analysis module 50 will be described in detail below. The semantic difference analysis module 50 may further include: calculating the semantic difference between any one of the screening sample temperature and humidity feature groups in the screening sample temperature and humidity feature group set and the remaining screening sample temperature and humidity feature groups to obtain a screening sample temperature and humidity feature group semantic difference set; taking a preset semantic difference set as a constraint, taking the screening sample information corresponding to the screening sample temperature and humidity feature group semantic difference lower than the preset semantic difference set in the screening sample temperature and humidity feature group semantic difference set as a new template to obtain a new template set; combining and paraphrasing the new template set to obtain the new sample abnormal information set.

[0044] Preferably, the set of screening sample temperature and humidity feature groups includes multiple screened abnormal temperature and humidity feature groups, and any one of the screening sample temperature and humidity feature groups is selected to calculate the semantic difference between this feature group and other screening sample temperature and humidity feature groups, that is, by comparing each pair of screening sample feature groups through cosine similarity, Euclidean distance, etc., to calculate the semantic difference between them, and quantify the difference between the two sample features in temperature and humidity data, wherein a high semantic difference indicates that the two samples have large differences in temperature and humidity features, and may represent two different types of anomalies; a low semantic difference indicates that the temperature and humidity features between the two samples are very similar, and may represent similar abnormal situations and belong to the same type of anomalies, thereby obtaining a set of semantic differences between the screening sample temperature and humidity feature groups, which contains a set of differences between all screening sample temperature and humidity feature groups. Through this set, it is possible to find out which samples have similar temperature and humidity features and which have large differences.

[0045] Preferably, a preset semantic difference set is used for constrained screening, wherein the preset semantic difference set is a pre-defined threshold set used to specify an acceptable maximum difference range. The set is used as a constraint condition to screen the semantic difference of the screening samples, and samples below the preset semantic difference threshold are used as new templates to represent potential abnormal types. The selected new template set is then combined and paraphrased, that is, these similar abnormal samples are "fused" and restated to expand the samples. Specifically, multiple similar sample features are merged or integrated to form a new abnormal pattern template, which helps to extract common features, simplify abnormal information, and enhance the universality of the pattern. Multiple abnormal samples are described as a concise and representative abnormal pattern or information through paraphrasing, and finally a new sample abnormal information set is obtained, which represents some specific types of abnormal patterns, provides a new template for the subsequent abnormal recognition system, and helps the system to more accurately identify and warn potential equipment abnormalities in the subsequent monitoring process.

[0046] The specific configuration of the semantic difference analysis module 50 will be described in detail below. The semantic difference analysis module 50 may further include: randomly combining the newly added template set in a preset combination mode to obtain a newly added combination sample abnormal information set, wherein the preset combination mode is to cross-reference any newly added template with at least two newly added templates; traversing and extracting keywords of the newly added template set to obtain a newly added template keyword group set, wherein each newly added template keyword group corresponds to a newly added template; performing random synonym conversion on the newly added template keyword group set, integrating the newly added template set according to the conversion result, and obtaining a newly added paraphrased sample abnormal information set; and using the newly added combination sample abnormal information set and the newly added paraphrased sample abnormal information set as the newly added sample abnormal information set.

[0047] Preferably, the newly added template set is randomly combined in a preset combination mode, that is, each newly added template is randomly cross-combined with at least two other newly added templates to generate multiple new abnormal samples, representing the intersection or comprehensive results of multiple abnormal patterns. Through random combination, different template features will be combined together to form new abnormal information, which can enrich the model of abnormal detection, capture more potential abnormal patterns, and enhance the recognition ability of the system; by traversing all newly added templates, the keywords in all templates are extracted and organized into a keyword group set, each newly added template will have a corresponding keyword group, indicating the core features of the template such as temperature and humidity changes. By extracting keywords, the core features of each template can be more accurately identified and understood, providing a basis for subsequent synonym conversion and information integration.

[0048] Preferably, synonym replacement is performed on the keyword group set of the newly added template. Synonym conversion refers to replacing some keywords in the template with words with the same or similar meanings, with the purpose of generating the same abnormal pattern with different expressions, for example, converting "temperature rise" into "temperature rise" and converting "high humidity" into "high humidity". Random conversion refers to converting by randomly selecting synonyms to avoid all templates being too simple or repetitive in expression, and providing a variety of different expressions for each abnormal template, so that the model can learn more variant abnormal patterns and improve its recognition and adaptability; the newly added combined sample abnormal information set (generated by random combination) and the newly added paraphrased sample abnormal information set (the set integrated by synonym conversion) are combined together to form a newly added sample abnormal information set, which includes abnormal information samples generated by different methods, covering the combined abnormal patterns and the diversified expressions generated by paraphrasing. Through this combination and integration, the system generates a highly diverse and representative abnormal sample set for training and optimizing models, helping the system to better identify and respond to different types of temperature and humidity anomalies, and enhancing the system's recognition and prediction capabilities.

[0049] The specific configuration of the monitoring and early warning network layer acquisition module 60 will be described in detail below. The monitoring and early warning network layer acquisition module 60 may further include: dividing the fusion sample abnormal information set into a training set and a verification set according to a preset ratio; constructing an initial monitoring and early warning network layer based on the training set; verifying the initial monitoring and early warning network layer based on the verification set, and if the verification passes, obtaining the trained monitoring and early warning network layer.

[0050] Preferably, the fused sample abnormal information set is divided into a training set and a validation set according to a preset ratio, usually 70% for training and 30% for validation. The training set contains most of the data and is used to train the model so that the model can learn the relationship between the input data and the target output. The validation set is used to evaluate the performance of the model during the training process to check whether the model is overfitting or whether it is too dependent on the training data. An initial monitoring and early warning network layer is constructed based on a deep learning model (such as a neural network), and the sample data in the training set is used to train it to learn how to identify abnormal patterns in temperature and humidity monitoring data. It usually includes an input layer (accepting temperature and humidity data) Samples are used as input), hidden layer (data is processed through multiple neurons and activation functions to extract the characteristics of abnormal patterns) and output layer (output abnormal or normal judgment results based on training samples, such as whether there are temperature and humidity abnormalities); the initial monitoring and early warning network layer is tested and verified using the validation set to evaluate the accuracy and stability of the initial model. When the initial monitoring and early warning network layer meets the preset performance standards on the validation set, it is considered that the verification has passed, and the trained monitoring and early warning network layer is obtained, indicating that it has learned how to identify and warn of abnormal temperature and humidity information, ensuring that the temperature and humidity data in the equipment room can be accurately detected and warned based on the trained network layer.

[0051] The specific configuration of the monitoring and early warning network layer acquisition module 60 will be described in detail below. The monitoring and early warning network layer acquisition module 60 may further include: traversing the training set to extract feature vectors, and performing mean processing on the extraction results to obtain concentrated feature vectors; introducing random noise vectors, combining the concentrated feature vectors to input the generator to generate interference samples, and obtaining interference sample sets; using the training set and the interference sample set to train the discriminator to obtain discrimination results, and obtaining discrimination loss coefficients based on the discrimination results; using the discrimination loss coefficients to iteratively update the network parameters of the discriminator and the generator until the preset number of iterations is met, and combining the generator and the discriminator that have completed the network parameter update to obtain the initial monitoring and early warning network layer that has completed the initial training.

[0052] Preferably, all sample data in the training set are traversed to extract the feature vector of each sample, which can reflect the core characteristics of the sample, which may include information such as temperature, humidity change pattern, abnormal peak value, etc. For example, for each sample, the temperature fluctuation amplitude, humidity change rate and other characteristics may be extracted. For all feature vectors in the training set, mean processing is performed, that is, the feature vectors of all samples are averaged to obtain a global average feature value, called a concentrated feature vector, which represents the average characteristics of the entire training set; then a random noise vector is introduced to provide a diverse input for the generator, thereby generating different samples to prevent the generator from always generating similar samples. Specifically, the generated random noise vector is combined with the obtained concentrated feature vector and input into the generator to generate new interference samples. These samples may be slightly different from the real samples in the training set and have a certain degree of randomness, thereby expanding the training set data so that the model can better learn various abnormal patterns and have stronger generalization ability.

[0053] Preferably, the task of the discriminator is to determine whether the input sample is a real sample (from the training set) or a generated sample (from the generator). Specifically, the training set and the interference sample set are used to train the discriminator together to learn how to distinguish between samples from real training data and interference samples generated by the generator. The output result of the discriminator is a judgment on whether the input sample is real. Usually a probability value is returned, indicating the possibility that the input sample is a real sample, and a discriminant loss coefficient is obtained based on the discrimination result. The loss coefficient is usually calculated based on the difference between the output result of the discriminator and the real label (that is, whether the sample is real) using a cross entropy loss function. The calculated discriminant loss coefficient is used to iteratively update the parameters of the generator and the discriminator using a back propagation algorithm, that is, the generator will adjust the parameters according to the feedback of the discriminator to make the generated samples more realistic, and the discriminator will optimize its own parameters according to the difference between the generated samples and the real samples to better distinguish between real and fake samples. This process continues until a preset number of iterations is reached, and the generator and the discriminator that have completed the network parameter update are combined to obtain a monitoring and early warning network layer that has completed the initial training, which can effectively identify and warn of temperature and humidity anomalies and help realize an intelligent monitoring and early warning system.

[0054] The specific configuration of the temperature and humidity feature extraction module 40 will be described in detail below. The temperature and humidity feature extraction module 40 may further include: pre-building a feature extraction network layer based on a convolutional neural network; using the feature extraction network layer to perform feature analysis on the screening sample abnormal information set to obtain the sample temperature and humidity feature group set.

[0055] Preferably, a convolutional neural network (CNN) is used for feature extraction, and the set of abnormal information of the screened samples is analyzed to finally obtain a set of temperature and humidity feature groups, wherein the convolutional neural network is a deep learning algorithm, which is particularly suitable for processing image data and time series data, that is, for extracting potential features in temperature and humidity data. Specifically, based on known abnormal data and background features, a feature extraction network layer is pre-constructed, and the network layer includes several convolution layers (for extracting local features) and pooling layers (for feature dimensionality reduction and abstraction), which can automatically identify meaningful features from the data; then the feature extraction network layer is used to perform feature extraction on the set of abnormal information of the screened samples; Feature analysis is to analyze each data sample in the screening sample abnormal information set, extract the key features of each sample, and identify patterns related to temperature and humidity anomalies from these samples through the convolutional neural network, such as sudden changes in temperature and humidity, long-term trend changes, periodic fluctuations, etc., and then obtain a set of sample temperature and humidity feature groups, which contains a data set of multiple different temperature and humidity feature groups. Each feature group represents the key features of a sample. For example, a feature group may include temperature change range, humidity fluctuation amplitude, temperature and humidity change rate, and temperature and humidity periodic change characteristics, which can help the system identify abnormal patterns and trends and improve the accuracy and robustness of anomaly detection.

[0056] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0057] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, 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 application should be included in the protection scope of this application.

Claims

1. The temperature and humidity monitoring and early warning system of the station equipment room is characterized by: The system comprises: A monitoring background feature set acquisition module is used to collect geographical environment features of the target station equipment room and obtain a monitoring background feature set based on the collection results; The abnormal temperature and humidity monitoring information set acquisition module is used to perform frequent item mining on big data using the monitoring background feature set as a label to obtain the abnormal temperature and humidity monitoring information set of the equipment room of the sample station; A sample quality verification and screening module is used to use an NLI filter in combination with the monitoring background feature set to perform sample quality verification and screening on the abnormal temperature and humidity monitoring information set of the equipment room of the sample station to obtain a screening sample abnormal information set; A temperature and humidity feature extraction module is used to extract temperature and humidity features from the screening sample abnormal information set to obtain a screening sample temperature and humidity feature group set; A semantic difference analysis module, used for performing semantic difference analysis on the temperature and humidity feature group set of the screened samples, and combining and paraphrasing the screened sample abnormal information set according to the analysis result to obtain a newly added sample abnormal information set, and fusing the newly added sample abnormal information set with the screened sample abnormal information set to obtain a fused sample abnormal information set; A monitoring and early warning network layer acquisition module is used to perform generative adversarial training of the monitoring and early warning network layer based on the fusion sample abnormal information set to obtain the trained monitoring and early warning network layer; The temperature and humidity monitoring and early warning module is used to use the sensor array to monitor the temperature and humidity of the target station equipment room, obtain the target temperature and humidity monitoring data, and use the monitoring and early warning network layer to perform abnormal analysis on the target temperature and humidity monitoring data, and perform temperature and humidity monitoring and early warning according to the analysis results.

2. The temperature and humidity monitoring and early warning system for the station equipment room as claimed in claim 1, characterized in that: The steps performed by the sample quality verification and screening module include: Generate hypothetical data and data labels based on the monitoring background feature set to obtain a hypothetical data set and a data label set, wherein the data labels include contradiction, implication and neutrality, and each hypothetical data corresponds to a data label; Using the hypothetical data set and the data label set to train the NLI recognizer built based on the BERT model until the training converges, thereby obtaining a trained NLI filter; Input the monitoring background feature set and the abnormal temperature and humidity monitoring information set of the sample station equipment room into the NLI filter to obtain a sample data label set; Based on the sample data label set, the sample station equipment room abnormal temperature and humidity monitoring information set is screened for sample quality verification to obtain a screened sample abnormal information set.

3. The temperature and humidity monitoring and early warning system for the station equipment room as claimed in claim 2, characterized in that: The steps performed by the sample quality verification and screening module include: When the sample data label in the sample data label set is implied, the corresponding sample station equipment room abnormal temperature and humidity monitoring information is added to the screening sample abnormal information set; When the sample data labels in the sample data label set are contradictory, the abnormal temperature and humidity monitoring information of the corresponding sample station equipment room will be eliminated; When the sample data label in the sample data label set is neutral, it will be sent to the sample quality verification personnel for manual verification. When the manual verification passes, the corresponding abnormal temperature and humidity monitoring information of the sample station equipment room will be added to the screening sample abnormal information set.

4. The temperature and humidity monitoring and early warning system for a station equipment room as claimed in claim 1, characterized in that: The steps performed by the semantic difference analysis module include: Calculating the semantic difference between any one of the screening sample temperature and humidity feature groups in the screening sample temperature and humidity feature group set and the remaining screening sample temperature and humidity feature groups to obtain a screening sample temperature and humidity feature group semantic difference set; Taking a preset semantic difference set as a constraint, taking the screening sample information corresponding to the semantic difference of the screening sample temperature and humidity feature group whose semantic difference is lower than the preset semantic difference set in the screening sample temperature and humidity feature group semantic difference set as a new template, to obtain a new template set; The newly added template set is combined and paraphrased to obtain the newly added sample abnormality information set.

5. The temperature and humidity monitoring and early warning system for the station equipment room as claimed in claim 4, characterized in that: The steps performed by the semantic difference analysis module include: The newly added template set is randomly combined according to a preset combination method to obtain a newly added combination sample abnormal information set, wherein the preset combination method is to cross-reference any one newly added template with at least two newly added templates; Traverse and extract keywords of the newly added template set to obtain a set of newly added template keyword groups, wherein each newly added template keyword group corresponds to a newly added template; Performing random synonym conversion on the newly added template keyword group set, integrating the newly added template set according to the conversion result, and obtaining a newly added paraphrase sample abnormal information set; The newly added combined sample anomaly information set and the newly added relayed sample anomaly information set are taken as the newly added sample anomaly information set.

6. The temperature and humidity monitoring and early warning system for a station equipment room as claimed in claim 1, characterized in that: The steps performed by the monitoring and early warning network layer acquisition module include: Dividing the fused sample abnormal information set into a training set and a validation set according to a preset ratio; Constructing an initial monitoring and early warning network layer based on the training set; The initial monitoring and early warning network layer is verified based on the verification set. If the verification passes, the trained monitoring and early warning network layer is obtained.

7. The temperature and humidity monitoring and early warning system for a station equipment room as claimed in claim 6, characterized in that: The steps performed by the monitoring and early warning network layer acquisition module include: Traversing the training set to extract feature vectors, and performing mean processing on the extraction results to obtain concentrated feature vectors; Introducing a random noise vector, combining it with the concentrated feature vector input into the generator to generate interference samples, and obtaining an interference sample set; Using the training set and the interference sample set to train the discriminator, obtain a discrimination result, and obtain a discrimination loss coefficient based on the discrimination result; The discriminant loss coefficient is used to iteratively update the network parameters of the discriminator and the generator until a preset number of iterations is met, and the generator and the discriminator that have completed the network parameter update are combined to obtain an initial monitoring and early warning network layer that has completed initial training.

8. The temperature and humidity monitoring and early warning system for a station equipment room as claimed in claim 1, characterized in that: The steps performed by the temperature and humidity feature extraction module include: Pre-build feature extraction network layer based on convolutional neural network; The feature extraction network layer is used to perform feature analysis on the abnormal information set of the screened samples to obtain the sample temperature and humidity feature group set.

Images