A device early warning monitoring system and method based on the Internet of Things

Abstract

An IoT-based equipment early warning monitoring system and method, which obtains the charging pile temperature values ​​and external environment temperature values ​​at multiple predetermined time points within a predetermined time period collected by a temperature sensor; performs data preprocessing on the charging pile temperature values ​​and external environment temperature values ​​at the multiple predetermined time points to obtain a charging pile temperature relative quantity time series input vector; extracts the charging pile temperature relative quantity local change characteristics of the charging pile temperature relative quantity time series input vector to obtain a sequence of charging pile temperature relative quantity local time series feature vectors; and, based on the sequence of charging pile temperature relative quantity local time series feature vectors, determines whether the working state of the charging pile is abnormal. In this way, the charging pile can be monitored and warned in real time through the IoT technology, so that corresponding repair and maintenance measures can be taken to improve the reliability and availability of the equipment.

Description

Technical Field

[0001] The present application relates to the field of intelligent early warning technology, and more specifically, to an equipment early warning monitoring system and method based on the Internet of Things. Background Art

[0002] A charging pile is a device used to provide electric energy for electric vehicles. Whether it works properly or not directly affects the safety and service life of electric vehicles. However, due to the complex and changeable working environment of the charging pile, its temperature change is affected by many factors, such as charging power, charging time, heat dissipation performance of the charging pile, external environment temperature, etc.

[0003] However, the traditional threshold-based temperature warning method is difficult to effectively determine whether the working state of the charging pile is abnormal, which is prone to missed reports or false reports. Therefore, an optimized early warning monitoring solution is expected. Summary of the invention

[0004] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides an equipment early warning monitoring system and method based on the Internet of Things, which obtains the charging pile temperature value and the external environment temperature value at multiple predetermined time points within a predetermined time period collected by a temperature sensor; performs data preprocessing on the charging pile temperature value and the external environment temperature value at the multiple predetermined time points to obtain the charging pile temperature relative quantity time series input vector; extracts the local change characteristics of the charging pile temperature relative quantity of the charging pile temperature relative quantity time series input vector to obtain a sequence of local time series feature vectors of the charging pile temperature relative quantity; and, based on the sequence of the local time series feature vectors of the charging pile temperature relative quantity, determines whether the working state of the charging pile is abnormal. In this way, the charging pile can be monitored and warned in real time through the Internet of Things technology, so that corresponding repair and maintenance measures can be taken to improve the reliability and availability of the equipment.

[0005] In a first aspect, a method for intelligently controlling a lighting driving power supply is provided, comprising:

[0006] Acquire the charging pile temperature value and the external environment temperature value collected by the temperature sensor at multiple predetermined time points within a predetermined time period;

[0007] Performing data preprocessing on the charging pile temperature values ​​and the external environment temperature values ​​at the plurality of predetermined time points to obtain a charging pile temperature relative quantity time series input vector;

[0008] Extracting the local variation characteristics of the relative temperature of the charging pile from the relative temperature time series input vector of the charging pile to obtain a sequence of local time series characteristic vectors of the relative temperature of the charging pile; and

[0009] Based on the sequence of the local time series feature vectors of the relative temperature quantity of the charging pile, it is determined whether there is an abnormality in the working state of the charging pile.

[0010] In the second aspect, a device early warning monitoring system based on the Internet of Things is provided, which includes:

[0011] A data acquisition module, used to acquire the temperature values ​​of the charging pile and the external environment at multiple predetermined time points within a predetermined time period collected by the temperature sensor;

[0012] A data preprocessing module, used for performing data preprocessing on the charging pile temperature values ​​and the external environment temperature values ​​at the plurality of predetermined time points to obtain a charging pile temperature relative quantity time series input vector;

[0013] A local change feature extraction module, used to extract the local change feature of the charging pile temperature relative quantity of the charging pile temperature relative quantity time series input vector to obtain a sequence of local time series feature vectors of the charging pile temperature relative quantity; and

[0014] The working state determination module is used to determine whether the working state of the charging pile is abnormal based on the sequence of the local time series feature vector of the relative temperature quantity of the charging pile. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 The present invention is a flowchart of an IoT-based device early warning monitoring method according to an embodiment of the present application.

[0017] Figure 2 Schematic diagram of the architecture of the device early warning monitoring method based on the Internet of Things according to an embodiment of the present application.

[0018] Figure 3 It is a block diagram of an IoT-based equipment early warning monitoring system according to an embodiment of the present application.

[0019] Figure 4 The present invention is a schematic diagram of a scenario of an IoT-based device early warning monitoring method according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] The following will describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0021] Unless otherwise specified, all technical and scientific terms used in the embodiments of the present application have the same meaning as those commonly understood by those skilled in the art of the present application. The terms used in this application are only for the purpose of describing specific embodiments and are not intended to limit the scope of this application.

[0022] In the embodiments of the present application, it should be noted that, unless otherwise specified and limited, the term "connection" should be understood in a broad sense. For example, it can be an electrical connection or a connection between two components. It can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to the specific circumstances.

[0023] It should be noted that the terms "first\second\third" involved in the embodiments of the present application are only used to distinguish similar objects, and do not represent a specific order for the objects. It is understandable that the specific order or sequence of "first\second\third" can be interchanged where permitted. It should be understood that the objects distinguished by "first\second\third" can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

[0024] A charging station is a device used to provide electric energy for charging electric vehicles or plug-in hybrid vehicles. It usually includes one or more charging plugs and a corresponding power management system that can transfer power from the power grid to the vehicle battery. The main function of a charging station is to provide power to charge electric vehicles to meet their driving energy needs. They are usually installed in parking lots, gas stations, commercial buildings, residential areas or public areas so that electric vehicle users can charge when needed.

[0025] Charging piles can be classified according to their charging speed and power output method. Slow Charging Station: Also known as home charging piles, they are usually used in residential areas or private parking lots. They provide lower charging power and longer charging time, which are suitable for use at night or when parking for a long time. Fast Charging Station: Provides higher charging power and can charge electric vehicles in a shorter time. Fast charging piles are usually installed in commercial areas or public charging stations so that users can get more charging power in a short time. Supercharger: This is a high-power fast charging pile developed by Tesla Electric Vehicle Company. They can charge Tesla electric vehicles at very high power and provide faster charging speed.

[0026] With the popularity of electric vehicles, the construction and development of charging piles have become increasingly important. They provide convenient charging facilities for electric vehicle users, promote the sustainable development of electric vehicles and reduce dependence on traditional fuel vehicles.

[0027] The traditional threshold-based temperature warning method is a simple method that determines whether the working state of the charging pile is abnormal based on the set temperature threshold. When the temperature of the charging pile exceeds the set threshold, the warning system will trigger an alarm to indicate that there may be a problem. However, this method has some limitations, which makes it difficult to effectively determine whether the working state of the charging pile is truly abnormal.

[0028] Traditional methods usually only consider the temperature of the charging pile as the basis for judgment, ignoring other important influencing factors. Factors such as charging power, charging time, heat dissipation performance of the charging pile, and external ambient temperature can affect the temperature change of the charging pile. Relying on a single indicator to judge the working status of the charging pile has limitations. Setting a suitable temperature threshold is a challenge. Charging piles of different models and specifications may have different temperature change ranges when working. If the threshold is set too low, it may cause false alarms; if the threshold is set too high, it may cause missed alarms. Therefore, setting a suitable threshold is crucial to accurately judge the working status of the charging pile. The temperature change of the charging pile is dynamic and is affected by many factors. Traditional methods cannot capture the dynamic characteristics of temperature changes, and it is difficult to accurately judge whether the working status of the charging pile is abnormal.

[0029] In order to address the limitations of traditional methods, an optimized early warning monitoring solution based on the Internet of Things and artificial intelligence technology can be adopted. This solution can establish a more accurate working status judgment model by real-time monitoring and analyzing multiple parameters such as the temperature change pattern, charging power, charging time, and external ambient temperature of the charging pile. Through machine learning algorithms or deep learning models, a large amount of data can be trained and learned to identify the abnormal working status of the charging pile, and timely issue early warning notifications so that corresponding repair and maintenance measures can be taken.

[0030] The traditional threshold-based temperature warning method has some limitations in judging whether the working status of the charging pile is abnormal. By adopting an optimized warning monitoring solution based on the Internet of Things and artificial intelligence technology, these limitations can be overcome and the reliability and availability of the charging pile can be improved.

[0031] Figure 1 The present invention is a flowchart of an IoT-based device early warning monitoring method according to an embodiment of the present application. Figure 2 FIG. 1 is a schematic diagram of the architecture of the device early warning monitoring method based on the Internet of Things according to an embodiment of the present application. Figure 1 and Figure 2 As shown, the IoT-based device early warning monitoring method includes: 110, acquiring the charging pile temperature value and the external environment temperature value at multiple predetermined time points within a predetermined time period collected by the temperature sensor; 120, performing data preprocessing on the charging pile temperature value and the external environment temperature value at the multiple predetermined time points to obtain a charging pile temperature relative quantity time series input vector; 130, extracting the charging pile temperature relative quantity local change characteristics of the charging pile temperature relative quantity time series input vector to obtain a sequence of charging pile temperature relative quantity local time series feature vectors; and, 140, determining whether the working state of the charging pile is abnormal based on the sequence of the charging pile temperature relative quantity local time series feature vectors.

[0032] In step 110, the temperature values ​​of the charging pile and the external environment at multiple predetermined time points within a predetermined time period are acquired by the temperature sensor. The accuracy and reliability of the temperature sensor are ensured to acquire accurate temperature data. At the same time, the predetermined time period and the predetermined time point are determined so that the temperature data can be acquired at these time points. By acquiring the temperature values ​​of the charging pile and the external environment, important data about the working status of the charging pile can be obtained. These data will be used for subsequent data preprocessing and analysis.

[0033] In step 120, data preprocessing is performed on the charging pile temperature values ​​and the external environment temperature values ​​at the plurality of predetermined time points to obtain a time series input vector of the relative amount of the charging pile temperature. Data preprocessing includes data cleaning, missing value processing, outlier processing, etc. The quality and integrity of the data are ensured for subsequent feature extraction and modeling analysis. Through data preprocessing, the reliability and accuracy of the data can be improved, and high-quality data can be provided for subsequent feature extraction and model training.

[0034] In step 130, the local change characteristics of the relative quantity of the charging pile temperature of the relative quantity of the charging pile temperature time series input vector are extracted to obtain a sequence of local time series characteristic vectors of the relative quantity of the charging pile temperature. The local change characteristics of the relative quantity of the charging pile temperature extracted may include statistical characteristics such as the mean value, standard deviation, maximum value, minimum value, etc., or the local time series characteristics may be extracted using a sliding window or other technology. Extracting the local change characteristics of the relative quantity of the charging pile temperature can capture the dynamic changes of the temperature, provide richer feature information, and facilitate subsequent abnormality detection and working status judgment.

[0035] In step 140, based on the sequence of the local time series feature vectors of the relative temperature of the charging pile, it is determined whether the working state of the charging pile is abnormal. The working state can be judged using methods such as machine learning algorithms, deep learning models or rule engines. By judging the working state based on the sequence of the local time series feature vectors of the relative temperature of the charging pile, abnormal detection and early warning of the charging pile can be achieved. This helps to promptly discover faults or abnormal conditions of the charging pile, take corresponding repair and maintenance measures, and improve the reliability and safety of the charging pile.

[0036] The Internet of Things (IoT) refers to a network of physical devices that are connected and interact with each other through the Internet. The IoT can connect various sensors, devices, and objects to achieve communication and data exchange between devices, thereby realizing intelligent and automated functions. The development of IoT technology provides a new idea for building an early warning monitoring solution for charging piles.

[0037] Based on this, the technical concept of this application is to use the Internet of Things technology to monitor and warn the charging pile in real time, so that corresponding repair and maintenance measures can be taken to improve the reliability and availability of the equipment. That is, the relationship between the temperature change pattern of the charging pile and the temperature change pattern of the external environment is analyzed with the help of the Internet of Things technology and artificial intelligence technology, so as to identify the abnormal working state of the charging pile.

[0038] Specifically, in the technical solution of the present application, firstly, the temperature values ​​of the charging pile and the external environment at multiple predetermined time points within a predetermined time period collected by the temperature sensor are obtained. Then, the temperature values ​​of the charging pile and the external environment at the multiple predetermined time points are preprocessed to obtain the time series input vector of the relative quantity of the charging pile temperature. That is, the time series discrete distribution of the charging pile temperature value and the time series discrete distribution of the external environment temperature value are converted into a structured vector representation to facilitate the reading and recognition of the subsequent model.

[0039] In a specific example of the present application, data preprocessing is performed on the charging pile temperature values ​​and the external environment temperature values ​​at the multiple predetermined time points to obtain an encoding process of a charging pile temperature relative quantity timing input vector, including: first arranging the charging pile temperature values ​​and the external environment temperature values ​​at the multiple predetermined time points into a charging pile temperature timing input vector and an external environment temperature timing input vector according to the time dimension respectively; and then calculating the position difference between the charging pile temperature timing input vector and the external environment temperature timing input vector to obtain the charging pile temperature relative quantity timing input vector.

[0040] Then, extract the local change characteristics of the relative quantity of the charging pile temperature of the relative quantity time series input vector of the charging pile temperature to obtain a sequence of local time series characteristic vectors of the relative quantity of the charging pile temperature. That is, capture the dynamic change pattern of the charging pile temperature in the time dimension from the relative quantity time series input vector of the charging pile temperature. It should be understood that when the charging pile is in normal working condition, its temperature will produce a certain change pattern over time. This change pattern is of great significance for judging whether there is an abnormality in the working state of the charging pile. It is worth mentioning that here, extracting local temperature time series change information helps the model to pay attention to more subtle temperature changes.

[0041] In a specific example of the present application, the encoding process of extracting the local change characteristics of the relative temperature of the charging pile from the time series input vector of the relative temperature of the charging pile to obtain a sequence of local time series feature vectors of the relative temperature of the charging pile includes: firstly vector segmenting the time series input vector of the relative temperature of the charging pile to obtain a sequence of local time series input vectors of the relative temperature of the charging pile; then, respectively passing the sequence of local time series input vectors of the relative temperature of the charging pile through a temperature time series pattern feature extractor based on a one-dimensional convolution layer to obtain a sequence of local time series feature vectors of the relative temperature of the charging pile. Here, a one-dimensional convolution layer is used to capture the local change pattern, which can perform a sliding window operation on the input data in the time dimension to extract local patterns and features. In this way, the local changes of the relative temperature of the charging pile can be effectively captured, including rising, falling, fluctuating and other patterns.

[0042] That is, in a specific embodiment of the present application, the local change characteristics of the relative temperature of the charging pile of the relative temperature time series input vector of the relative temperature of the charging pile are extracted to obtain a sequence of local time series characteristic vectors of the relative temperature of the charging pile, including: vector segmentation of the relative temperature of the charging pile of the relative temperature time series input vector to obtain a sequence of local time series input vectors of the relative temperature of the charging pile; and, extracting the local time series characteristics of the relative temperature of the charging pile of the sequence of local time series input vectors of the relative temperature of the charging pile to obtain a sequence of local time series characteristic vectors of the relative temperature of the charging pile.

[0043] Among them, extracting the local time series characteristics of the charging pile temperature relative quantity of the sequence of the local time series input vectors of the charging pile temperature relative quantity to obtain the sequence of the local time series feature vectors of the charging pile temperature relative quantity, including: passing the sequence of the local time series input vectors of the charging pile temperature relative quantity through a temperature time series pattern feature extractor based on a one-dimensional convolutional layer to obtain the sequence of the local time series feature vectors of the charging pile temperature relative quantity.

[0044] In a specific embodiment of the present application, based on the sequence of local time series feature vectors of the relative temperature of the charging pile, determining whether there is an abnormality in the working state of the charging pile, includes: extracting the full time domain characteristics of the charging pile temperature pattern change from the sequence of local time series feature vectors of the relative temperature of the charging pile to obtain a full time domain semantic feature vector of the charging pile temperature pattern characteristics; and passing the full time domain semantic feature vector of the charging pile temperature pattern characteristics through a classifier to obtain a classification result, and the classification result is used to indicate whether there is an abnormality in the working state of the charging pile.

[0045] Among them, the full time domain characteristics of the charging pile temperature pattern change are extracted from the sequence of the local time series feature vectors of the charging pile temperature relative quantity to obtain the full time domain semantic feature vector of the charging pile temperature pattern characteristics, including: passing the sequence of the local time series feature vectors of the charging pile temperature relative quantity through a Bi-LSTM-based time context encoder to obtain the full time domain semantic feature vector of the charging pile temperature pattern characteristics.

[0046] Furthermore, the sequence of the local time series feature vectors of the relative temperature of the charging pile is passed through a Bi-LSTM-based time series context encoder to obtain the full-time domain semantic feature vector of the temperature pattern feature of the charging pile. That is, the full-time domain features of the temperature pattern change of the charging pile are extracted from the sequence of the local time series feature vectors of the relative temperature of the charging pile, and the overall change pattern of the temperature of the charging pile is learned. Then, the full-time domain semantic feature vector of the temperature pattern feature of the charging pile is passed through a classifier to obtain a classification result, and the classification result is used to indicate whether there is an abnormality in the working state of the charging pile.

[0047] In the technical solution of the present application, after the sequence of the local time series input vectors of the relative quantity of the charging pile temperature passes through the temperature time series pattern feature extractor based on the one-dimensional convolutional layer, the sequence of the local time series feature vectors of the relative quantity of the charging pile temperature obtained can express the time series correlation characteristics of the relative quantity of the charging pile temperature in the local time domain under the global time domain. Therefore, the sequence of the local time series feature vectors of the relative quantity of the charging pile temperature passes through the time series context encoder based on Bi-LSTM, which can further extract the local time domain context correlation of the time series characteristics of the relative quantity of the charging pile temperature under the global time domain, so that the full time domain semantic feature vector of the charging pile temperature pattern feature has a multi-scale time series correlation expression within the local time domain and between local time domains. However, this multi-scale time series correlation expression within the local time domain and between local time domains of the full time domain semantic feature vector of the charging pile temperature pattern feature will cause the full time domain semantic feature vector of the charging pile temperature pattern feature to be offset relative to the predetermined category harmony of the classifier due to the difference in correlation accuracy of the local time series correlation features of different scales when passing through the classifier, affecting the classification iteration effect.

[0048] In a preferred embodiment, the full-time domain semantic feature vector of the charging pile temperature pattern feature is passed through a classifier to obtain a classification result, including the following steps: first, the autocorrelation matrix of the full-time domain semantic feature vector of the charging pile temperature pattern feature and its own transposition is calculated, and the inner product of the i-th and j-th row vectors of the autocorrelation matrix is ​​calculated as the matrix value of the (i, j)-th position of the weight matrix to obtain a weight matrix, then, after matrix multiplication of the weight matrix and the autocorrelation matrix, further matrix-vector multiplication is performed with the full-time domain semantic feature vector of the charging pile temperature pattern feature to obtain a correction vector, finally, the correction vector is dot-multiplied with the full-time domain semantic feature vector of the charging pile temperature pattern feature to obtain an optimized full-time domain semantic feature vector of the charging pile temperature pattern feature, and the optimized full-time domain semantic feature vector of the charging pile temperature pattern feature is passed through a classifier to obtain a classification result.

[0049] The optimization steps are specifically expressed as follows:

[0050]

[0051] Among them, V represents the full-time semantic feature vector of the charging pile temperature pattern feature, T represents the transpose of the vector, M represents the autocorrelation matrix, and V i and V j represents the i-th and j-th row vectors of the autocorrelation matrix, M′ represents the weight matrix, m i，j represents the matrix value of the (i, j)th position of the weight matrix, L represents the height of the autocorrelation matrix, R represents a set of real numbers, represents matrix multiplication, ⊙ represents dot product, and V′ represents the optimized full-time domain semantic feature vector of charging pile temperature pattern features.

[0052] Based on the self-correlation dimension of the full-time domain semantic feature vector of the charging pile temperature pattern feature as the object to be modulated, correlation expansion is performed based on the spatial sub-dimensional complexity of the high-dimensional feature space of the feature distribution, thereby introducing the decomposable correlation dimension offset of the full-time domain semantic feature vector of the charging pile temperature pattern feature into the heterogeneous correlation embedding space, thereby enhancing the correlation self-consistency through the joint fine-tuning of the decomposable dimension set represented by the heterogeneous correlation embedding space, so as to improve the predetermined category harmony of the feature set of the full-time domain semantic feature vector of the charging pile temperature pattern feature in the associated target classification domain, thereby improving the classification training speed and the accuracy of the classification result when the full-time domain semantic feature vector of the charging pile temperature pattern feature is classified by the classifier.

[0053] In summary, the device early warning monitoring method based on the Internet of Things according to the embodiment of the present application is explained, which uses the Internet of Things technology to monitor and warn the charging pile in real time, so that corresponding repair and maintenance measures can be taken to improve the reliability and availability of the equipment. That is, the relationship between the temperature change pattern of the charging pile and the temperature change pattern of the external environment is analyzed by using the Internet of Things technology and artificial intelligence technology, so as to identify the abnormal working state of the charging pile.

[0054] In one embodiment of the present application, Figure 3 FIG. 1 is a block diagram of an IoT-based device early warning monitoring system according to an embodiment of the present application. Figure 3 As shown, according to the embodiment of the present application, the IoT-based equipment early warning monitoring system 200 includes: a data acquisition module 210, which is used to obtain the charging pile temperature value and the external environment temperature value at multiple predetermined time points within a predetermined time period collected by the temperature sensor; a data preprocessing module 220, which is used to perform data preprocessing on the charging pile temperature value and the external environment temperature value at the multiple predetermined time points to obtain the charging pile temperature relative quantity time series input vector; a local change feature extraction module 230, which is used to extract the local change feature of the charging pile temperature relative quantity of the charging pile temperature relative quantity time series input vector to obtain a sequence of the charging pile temperature relative quantity local time series feature vector; and a working state determination module 240, which is used to determine whether the working state of the charging pile is abnormal based on the sequence of the charging pile temperature relative quantity local time series feature vector.

[0055] In the IoT-based equipment early warning monitoring system, the data preprocessing module includes: a vector arrangement unit, which is used to arrange the charging pile temperature values ​​and the external environment temperature values ​​at the multiple predetermined time points into a charging pile temperature timing input vector and an external environment temperature timing input vector according to the time dimension; and a difference calculation unit, which is used to calculate the positional difference between the charging pile temperature timing input vector and the external environment temperature timing input vector to obtain the charging pile temperature relative quantity timing input vector.

[0056] In one embodiment of the present application, a charging pile early warning monitoring system is provided, which mainly includes several functional modules:

[0057] 1. Data collection: mainly collects the operation status of the installed charging piles, such as whether there are any broken ones or those that do not meet the operation standards. This collection is mainly manual and has been running for two or three years. Therefore, the original database of the existing charging piles in Shenzhen has been prepared. Now it is sufficient to collect and inspect them every month.

[0058] 2. During manual on-site data collection and verification inspections, the operating conditions of the equipment and whether they still meet the standards are collected in accordance with industry standards and national standards. The collected content is not innovative or self-designed.

[0059] 3. Upload module, supports uploading physical forms, on-site photos, punch-in photos, etc., and the uploaded forms are automatically entered into the system. When entering the system, in addition to the form of equipment operation status, form fields are also set to facilitate internal management;

[0060] 4. Data processing and analysis module, based on the data collected and inspected, determines whether there is any equipment abnormality;

[0061] 5. Early warning module, which summarizes and provides feedback on early warning information based on abnormal information;

[0062] 6. The inspection and warning results export module can automatically export the inspection and warning results and automatically generate reports for supervision and management and law enforcement departments to use

[0063] 7. A dashboard module was created, where you can view the conclusions of multiple modules in real time.

[0064] 8. In the management background, set a series of fields and labels, so that the entire project, except for on-site collection and inspection, needs to be manually processed on-site, and other work should be automated or semi-automated as much as possible, such as the management of imported data information, the generation of early warning information, the management of order placement, dispatch management, and the management of early warning information feedback, etc.

[0065] Furthermore, the charging pile early warning monitoring system is a system that uses Internet of Things technology and big data analysis to conduct real-time monitoring and early warning of the operating status, fault information, safety risks, etc. of the charging pile. The system consists of the following parts:

[0066] Charging pile terminal: An intelligent device installed on the charging pile, responsible for collecting various parameters of the charging pile, such as voltage, current, temperature, humidity, smoke, etc., and transmitting the data to the cloud platform through a wireless network.

[0067] Cloud platform: responsible for receiving and storing data sent by charging pile terminals, as well as analyzing and processing the data. It evaluates and judges the operating status of the charging piles according to preset rules and algorithms. If any abnormality or failure is found, it will generate early warning information in a timely manner and notify relevant personnel via SMS, email, phone, etc.

[0068] Monitoring center: responsible for displaying and managing the monitoring data and warning information of charging piles, as well as providing remote control and maintenance functions. The monitoring center can be a physical place, or a webpage or mobile application.

[0069] Relevant personnel: including charging pile operators, maintenance personnel, users, etc., can view and process the monitoring data and early warning information of the charging piles, as well as perform remote control and maintenance according to different roles and permissions.

[0070] Here, those skilled in the art can understand that the specific functions and operations of each unit and module in the above-mentioned IoT-based equipment early warning monitoring system have been referred to above. Figure 1 to Figure 2 The description of the IoT-based device early warning monitoring method has been introduced in detail, and therefore, its repeated description will be omitted.

[0071] As described above, the device early warning monitoring system 200 based on the Internet of Things according to the embodiment of the present application can be implemented in various terminal devices, such as a server for device early warning monitoring based on the Internet of Things. In one example, the device early warning monitoring system 200 based on the Internet of Things according to the embodiment of the present application can be integrated into the terminal device as a software module and / or a hardware module. For example, the device early warning monitoring system 200 based on the Internet of Things can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the device early warning monitoring system 200 based on the Internet of Things can also be one of the many hardware modules of the terminal device.

[0072] Alternatively, in another example, the IoT-based device early warning monitoring system 200 and the terminal device may also be separate devices, and the IoT-based device early warning monitoring system 200 may be connected to the terminal device via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0073] Figure 4 FIG. 1 is a schematic diagram of a scenario of a device early warning monitoring method based on the Internet of Things according to an embodiment of the present application. Figure 4 As shown, in this application scenario, first, the charging pile temperature values ​​collected by the temperature sensor at multiple predetermined time points within a predetermined time period are obtained (for example, Figure 4 C1) and the ambient temperature (e.g. Figure 4 Then, the obtained charging pile temperature value and the external environment temperature value are input to a server (for example, Figure 4 In the S) shown in , the server can process the charging pile temperature value and the external environment temperature value based on the device early warning monitoring algorithm of the Internet of Things to determine whether there is any abnormality in the working state of the charging pile.

[0074] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0075] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0076] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A device early warning monitoring method based on the Internet of Things, characterized in that: include: Acquire the charging pile temperature value and the external environment temperature value collected by the temperature sensor at multiple predetermined time points within a predetermined time period; Performing data preprocessing on the charging pile temperature values ​​and the external environment temperature values ​​at the plurality of predetermined time points to obtain a charging pile temperature relative quantity time series input vector; Extracting the local change characteristics of the relative temperature of the charging pile from the relative temperature time series input vector of the charging pile to obtain a sequence of local time series characteristic vectors of the relative temperature of the charging pile; as well as Based on the sequence of the local time series feature vector of the relative temperature quantity of the charging pile, determining whether the working state of the charging pile is abnormal; Determining whether there is an abnormality in the working state of the charging pile based on the sequence of the local time series feature vector of the relative temperature quantity of the charging pile includes: Extracting the full-time domain feature of the charging pile temperature pattern change from the sequence of the local time series feature vectors of the charging pile temperature relative quantity to obtain the full-time domain semantic feature vector of the charging pile temperature pattern feature; and Passing the full-time domain semantic feature vector of the charging pile temperature pattern feature through a classifier to obtain a classification result, wherein the classification result is used to indicate whether there is an abnormality in the working state of the charging pile; The full-time domain semantic feature vector of the charging pile temperature pattern feature is passed through a classifier to obtain a classification result, comprising the following steps: firstly calculating the autocorrelation matrix of the full-time domain semantic feature vector of the charging pile temperature pattern feature and its own transposition, and calculating the first and The inner product of the row vectors is used as the weight matrix The matrix value of the position is obtained to obtain a weight matrix, and then the weight matrix is ​​matrix-multiplied with the autocorrelation matrix, and then further matrix-vector multiplied with the charging pile temperature pattern feature full time domain semantic feature vector to obtain a correction vector, and finally the correction vector is dot-multiplied with the charging pile temperature pattern feature full time domain semantic feature vector to obtain an optimized charging pile temperature pattern feature full time domain semantic feature vector, and the optimized charging pile temperature pattern feature full time domain semantic feature vector is passed through a classifier to obtain a classification result.

2. The device early warning monitoring method based on the Internet of Things according to claim 1 is characterized in that: The charging pile temperature values ​​and the external environment temperature values ​​at the plurality of predetermined time points are subjected to data preprocessing to obtain a charging pile temperature relative quantity time series input vector, including: Arrange the charging pile temperature values ​​and the external environment temperature values ​​at the plurality of predetermined time points into a charging pile temperature time series input vector and an external environment temperature time series input vector according to the time dimension; and The position difference between the charging pile temperature time series input vector and the external environment temperature time series input vector is calculated to obtain the charging pile temperature relative quantity time series input vector.

3. The device early warning monitoring method based on the Internet of Things according to claim 2 is characterized in that: Extracting the local change characteristics of the relative temperature of the charging pile from the relative temperature time series input vector of the charging pile to obtain a sequence of local time series characteristic vectors of the relative temperature of the charging pile, including: Performing vector segmentation on the charging pile temperature relative quantity time series input vector to obtain a sequence of charging pile temperature relative quantity local time series input vectors; and The local time series features of the relative temperature of the charging piles are extracted from the sequence of the local time series input vectors of the relative temperature of the charging piles to obtain a sequence of the local time series feature vectors of the relative temperature of the charging piles.

4. The device early warning monitoring method based on the Internet of Things according to claim 3 is characterized in that: Extracting the local time series features of the relative temperature of the charging pile from the sequence of the local time series input vectors of the relative temperature of the charging pile to obtain the sequence of the local time series feature vectors of the relative temperature of the charging pile, including: The sequence of the local time series input vectors of the relative temperature of the charging pile is respectively passed through a temperature time series pattern feature extractor based on a one-dimensional convolutional layer to obtain a sequence of the local time series feature vectors of the relative temperature of the charging pile.

5. The device early warning monitoring method based on the Internet of Things according to claim 4 is characterized in that: Extracting the full-time domain feature of the charging pile temperature pattern change from the sequence of the local time series feature vector of the charging pile temperature relative quantity to obtain the full-time domain semantic feature vector of the charging pile temperature pattern feature, including: The sequence of the local time series feature vectors of the relative temperature of the charging pile is passed through a Bi-LSTM-based time series context encoder to obtain the full time domain semantic feature vector of the charging pile temperature pattern feature.

6. An IoT-based equipment early warning monitoring system, characterized in that: include: A data acquisition module, used to acquire the charging pile temperature value and the external environment temperature value at multiple predetermined time points within a predetermined time period collected by the temperature sensor; A data preprocessing module, used for performing data preprocessing on the charging pile temperature values ​​and the external environment temperature values ​​at the plurality of predetermined time points to obtain a charging pile temperature relative quantity time series input vector; A local change feature extraction module, used to extract the local change feature of the charging pile temperature relative quantity of the charging pile temperature relative quantity time series input vector to obtain a sequence of local time series feature vectors of the charging pile temperature relative quantity; as well as A working state determination module, used to determine whether the working state of the charging pile is abnormal based on the sequence of the local time series feature vector of the relative temperature quantity of the charging pile; The working status determination module is used to: Extracting the full-time domain feature of the charging pile temperature pattern change from the sequence of the local time series feature vectors of the charging pile temperature relative quantity to obtain the full-time domain semantic feature vector of the charging pile temperature pattern feature; and Passing the full-time domain semantic feature vector of the charging pile temperature pattern feature through a classifier to obtain a classification result, wherein the classification result is used to indicate whether there is an abnormality in the working state of the charging pile; The working state determination module is used to: first calculate the autocorrelation matrix of the full-time domain semantic feature vector of the charging pile temperature pattern feature and its own transposition, and calculate the first and The inner product of the row vectors is used as the weight matrix The matrix value of the position is obtained to obtain a weight matrix, and then the weight matrix is ​​matrix-multiplied with the autocorrelation matrix, and then further matrix-vector multiplied with the charging pile temperature pattern feature full time domain semantic feature vector to obtain a correction vector, and finally the correction vector is dot-multiplied with the charging pile temperature pattern feature full time domain semantic feature vector to obtain an optimized charging pile temperature pattern feature full time domain semantic feature vector, and the optimized charging pile temperature pattern feature full time domain semantic feature vector is passed through a classifier to obtain a classification result.

7. The IoT-based equipment early warning monitoring system according to claim 6, characterized in that: The data preprocessing module comprises: A vector arrangement unit, configured to arrange the charging pile temperature values ​​and the external environment temperature values ​​at the plurality of predetermined time points into a charging pile temperature time series input vector and an external environment temperature time series input vector according to a time dimension; and The difference calculation unit is used to calculate the position difference between the charging pile temperature time series input vector and the external environment temperature time series input vector to obtain the charging pile temperature relative quantity time series input vector.

Images