Meter box real-time monitoring method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a meter box real-time monitoring method and device, electronic equipment and a storage medium, and the device comprises a multi-modal data collection module which is used for collecting multi-modal data; the control module is connected with the multi-modal data acquisition module, and the control module is used for controlling the multi-modal data acquisition module; the communication module is connected with the multi-modal data acquisition module and the server, the communication module is used for realizing communication between the control module and the server, the server is used for interacting with monitoring personnel, and the method comprises the following steps: carrying out rotational training detection on the multi-modal data acquired by the multi-modal data acquisition module to obtain a detection result; and performing exception handling according to a preset exception handling strategy in response to the detection result indicating that the multi-modal data is abnormal. The technical problems that in the prior art, a technical scheme for carrying out all-around safety monitoring on the meter box is lacked, and the safety risk of the meter box cannot be found in time are solved.

Description

Technical Field

[0001] The present invention belongs to the field of electrical technology, and in particular, relates to a real-time monitoring method, device, electronic equipment and storage medium for a meter box. Background Art

[0002] At present, in areas with frequent thunderstorms, high salt and high humidity, the meter boxes in the dedicated transformer substation and the public transformer substation are prone to rust and the installation location of the meter boxes is relatively remote, which affects the stability and reliability of the meter boxes. There are several specific problems: (1) Due to peak electricity consumption, the load in the user substation and the public transformer substation increases, and even overloads, causing line overheating; due to line joints, the three-phase four-wire meter box catches fire, causing large-scale power outages in the substation or affecting the safe operation of the metering device. (2) In harsh environments, small animals often enter the meter box, which will cause phase-to-phase short circuits to a certain extent, posing a great safety hazard to the meter box. (3) There is a risk of electricity theft in the dedicated transformer user meter box, which is difficult to detect and obtain evidence; these abnormal situations result in certain economic and social benefit losses.

[0003] In summary, the prior art lacks a technical solution for conducting all-round safety monitoring of the meter box, and the safety risks of the meter box cannot be discovered in a timely manner. Summary of the invention

[0004] The embodiments of the present invention provide a real-time monitoring method, device, electronic device and storage medium for a meter box, so as to at least solve the technical problem that the prior art lacks a technical solution for comprehensive safety monitoring of the meter box and the safety risks of the meter box cannot be discovered in time.

[0005] According to a first aspect of an embodiment of the present invention, a real-time monitoring method for a meter box is provided, comprising: performing round-robin detection on multimodal data collected by a multimodal data acquisition module to obtain a detection result; in response to the detection result indicating that the multimodal data is abnormal, performing exception handling according to a preset exception handling strategy.

[0006] Optionally, in response to the detection result indicating that there is an abnormality in the multimodal data, exception handling is performed according to a preset exception handling strategy, including: in response to the detection result indicating that there is an abnormality in the photoelectric sensing switch data, based on the preset exception handling strategy, controlling the camera to turn on and acquire image data, and at the same time controlling the indicator light to change color, wherein the photoelectric sensing switch data is included in the multimodal data.

[0007] Optionally, in response to the detection result indicating that the multimodal data has an abnormality, the exception is handled according to a preset exception handling strategy, including: in response to the detection result indicating that the millimeter-wave sensing radar data has an abnormality, based on the preset exception handling strategy, starting the sound and light alarm module and the ultrasonic expulsion device, and controlling the indicator light to change color, wherein the millimeter-wave sensing radar data is included in the multimodal data.

[0008] Optionally, the fault is handled according to a preset strategy, including: in response to the detection results indicating that there are abnormalities in the temperature and humidity sensor data, water immersion sensor data, and smoke sensor data, based on a preset abnormality handling strategy, controlling the indicator light to change color, wherein the temperature and humidity sensor data, water immersion sensor data, and smoke sensor data are included in the multimodal data.

[0009] Optionally, the real-time monitoring method for the meter box also includes: extracting features from the image data to obtain feature data; and determining an image recognition result based on the feature data using a preset image recognition model, wherein the image recognition result is used to determine whether a fire exists.

[0010] According to the second aspect of an embodiment of the present invention, a real-time monitoring device for a meter box is also provided, including: a multimodal data acquisition module, used to collect multimodal data; a control module, connected to the multimodal data acquisition module, the control module is used to control the multimodal data acquisition module; a communication module, connected to the multimodal data acquisition module and to a server, the communication module is used to realize communication between the control module and the server, and the server is used to interact with monitoring personnel.

[0011] Optionally, the multimodal data acquisition module includes a smoke sensor, an infrared sensor, a radar sensor, a temperature and humidity sensor, a water immersion sensor, a camera, an ultrasonic sensor, an acoustic and optical sensor, and a positioning module.

[0012] According to a third aspect of an embodiment of the present invention, there is also provided an electronic device, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the real-time monitoring method for a meter box as described in any embodiment of the first aspect above.

[0013] According to a fourth aspect of an embodiment of the present invention, a non-volatile storage medium is also provided, in which a computer program is stored, wherein the computer program is configured to execute the real-time monitoring method for the meter box described in any embodiment of the first aspect when running on a computer or processor.

[0014] According to a fifth aspect of an embodiment of the present invention, a computer program product is also provided, including a computer program, which, when executed by a processor, implements the real-time monitoring method for a meter box as described in any embodiment of the first aspect above.

[0015] In an embodiment of the present invention, the multimodal data collected by the multimodal data collection module is subjected to round-robin detection to obtain a detection result; in response to the detection result indicating that the multimodal data is abnormal, the abnormality is handled according to a preset abnormality handling strategy. By detecting the multimodal data and handling the abnormal situation, the safety risks of the meter box can be detected from multiple aspects, the safety risks can be discovered in time, and the safety risks can be handled according to the preset strategy, which solves the technical problem that the prior art lacks a technical solution for all-round safety monitoring of the meter box and the safety risks of the meter box cannot be discovered in time. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are provided to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0017] Figure 1 is a flow chart of a real-time monitoring method for a meter box according to one embodiment of the present invention;

[0018] Figure 2 is a structural block diagram of a real-time monitoring device for a meter box according to one embodiment of the present invention;

[0019] Figure 3 is a schematic diagram of the hardware structure of a real-time monitoring device for a meter box according to one embodiment of the present invention;

[0020] Figure 4 It is an example flow chart of a real-time monitoring method for a meter box according to one embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are set to distinguish similar objects, and are not necessarily set to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device 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 units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] According to an embodiment of the present invention, an embodiment of a real-time monitoring method for a meter box is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system comprising at least one set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0024] The method embodiment can also be executed in an electronic device including a memory and a processor, a similar control device or a cloud. Taking an electronic device as an example, the electronic device may include one or more processors and a memory configured to store data. Optionally, the electronic device may also include a communication device configured to have a communication function and a display device. It will be understood by those of ordinary skill in the art that the above structural description is only illustrative and does not limit the structure of the above electronic device. For example, the electronic device may also include more or fewer components than the above structural description, or have a configuration different from the above structural description.

[0025] The processor may include one or more processing units. For example, the processor may include a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP) chip, a microcontroller unit (MCU), a field-programmable gate array (FPGA), a neural network processor (NPU), a tensor processing unit (TPU), an artificial intelligence (AI) type processor, and the like. Among them, different processing units may be independent components or integrated into one or more processors. In some instances, the electronic device may also include one or more processors.

[0026] The memory may be configured to store a computer program, for example, a computer program corresponding to the real-time monitoring method for a meter box in an embodiment of the present invention is stored. The processor implements the real-time monitoring method for a meter box by running the computer program stored in the memory. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0027] The communication device is configured to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the communication device includes a network adapter (network interface controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the communication device can be a radio frequency (radio frequency, RF) module, which is configured to communicate with the Internet wirelessly. In some embodiments of the present solution, the communication device is configured to be connected to a mobile device such as a mobile phone, a tablet, and instructions can be sent to the electronic device through the mobile device.

[0028] The display device may be a touch screen type liquid crystal display (LCD) and a touch display (also referred to as a "touch screen" or "touch display screen"). The liquid crystal display may enable a user to interact with a user interface of the electronic device. In some embodiments, the electronic device has a graphical user interface (GUI), and a user may interact with the GUI by touching a finger release and / or gestures on a touch-sensitive surface, and executable instructions configured to perform the above-mentioned human-computer interaction functions are configured / stored in a computer program product or a readable storage medium executable by one or more processors.

[0029] Figure 1 : is a flow chart of a real-time monitoring method for a meter box according to one embodiment of the present invention. Figure 1 As shown, the following steps are included:

[0030] Step S101, performing round-robin detection on the multimodal data collected by the multimodal data collection module to obtain a detection result.

[0031] Step S102: in response to the detection result indicating that the multimodal data is abnormal, the abnormality is handled according to a preset abnormality handling strategy.

[0032] In an embodiment of the present invention, the multimodal data collected by the multimodal data collection module is subjected to round-robin detection to obtain a detection result; in response to the detection result indicating that the multimodal data is abnormal, the abnormality is handled according to a preset abnormality handling strategy. By detecting the multimodal data and handling the abnormal situation, the safety risks of the meter box can be detected from multiple aspects, the safety risks can be discovered in time, and the safety risks can be handled according to the preset strategy, which solves the technical problem that the prior art lacks a technical solution for all-round safety monitoring of the meter box and the safety risks of the meter box cannot be discovered in time.

[0033] Optionally, in response to the detection result indicating that there is an abnormality in the multimodal data, exception handling is performed according to a preset exception handling strategy, including: in response to the detection result indicating that there is an abnormality in the photoelectric sensing switch data, based on the preset exception handling strategy, controlling the camera to turn on and acquire image data, and at the same time controlling the indicator light to change color, wherein the photoelectric sensing switch data is included in the multimodal data.

[0034] Optionally, in response to the detection result indicating that the multimodal data has an abnormality, the exception is handled according to a preset exception handling strategy, including: in response to the detection result indicating that the millimeter-wave sensing radar data has an abnormality, based on the preset exception handling strategy, starting the sound and light alarm module and the ultrasonic expulsion device, and controlling the indicator light to change color, wherein the millimeter-wave sensing radar data is included in the multimodal data.

[0035] Optionally, the fault is handled according to a preset strategy, including: in response to the detection results indicating that there are abnormalities in the temperature and humidity sensor data, water immersion sensor data, and smoke sensor data, based on a preset abnormality handling strategy, controlling the indicator light to change color, wherein the temperature and humidity sensor data, water immersion sensor data, and smoke sensor data are included in the multimodal data.

[0036] Optionally, the real-time monitoring method for the meter box also includes: extracting features from the image data to obtain feature data; and determining an image recognition result based on the feature data using a preset image recognition model, wherein the image recognition result is used to determine whether a fire exists.

[0037] Specifically, refer to Figure 4 The method described in the above embodiment is exemplarily performed as follows:

[0038] (1) System initialization. When the system starts, perform the following initialization steps to ensure the normal operation of the system. Hardware configuration: Set the system clock to ensure that the microcontroller starts correctly. Peripheral configuration: Configure GPIO, UART and other peripherals to prepare for data input and output. (2) Main loop process. Input processing: Read from the photoelectric sensor switch whether the door of the electrical box is detected to be open. Poll the millimeter wave sensing radar to determine whether an object is moving. Read the temperature and humidity values ​​of the temperature and humidity sensor to detect whether there is abnormal temperature. Poll the smoke sensor to determine whether there is suspicious gas. Poll the water sensor to determine whether the electrical box is submerged in water. Data processing: Analyze the data captured by the camera. According to the polling results, process the data of the temperature and humidity module, water sensor and smoke sensor. Output control: According to the processing results, control the relay module, sound and light alarm, LED status indicator, etc. (3) Functional module. The system consists of multiple functional modules that work together to achieve the monitoring purpose. Communication module: Exchange data with the 4G communication DTU through the serial port protocol to send warning information. Control module: controls output devices such as LED status indicators, sound and light alarms, etc. according to the processing results.

[0039] It should be noted that the image data collected by the camera is analyzed and processed using computer technology, and the fire image data set is uploaded to the HDFS file system. Then, based on the difference between the flame image and common interfering substances, the color features, texture features and Sift features of the image are extracted as the criteria for identifying the flame image; finally, the optimal SVM classification model is obtained through the MFFRW algorithm, so as to accurately identify the fire flame image. The fire image has a high recognition rate and recognition speed, can cope with a large range of fire monitoring, and achieve the purpose of early fire alarm.

[0040] The above algorithm is specifically implemented as follows:

[0041] 1. Feature extraction

[0042] (1) Color feature extraction

[0043] The color characteristics of the flame image are modeled by the distribution of its RGB values. We use a color histogram to represent the color characteristics of the image:

[0044] H color =[h R (i),h G (i),h B (i)]

[0045] Among them, h R (i),h G (i),h B (i) is the pixel value distribution of the image in the red, green and blue channels, respectively, and i is the color level (0-255).

[0046] In order to capture the color characteristics of the flame more clearly, we normalize the pixel density of the red channel:

[0047]

[0048] From the experimental results, we can know that the red pixel density of the flame image is concentrated in the high brightness area (i≥200), that is:

[0049]

[0050] (2) Texture feature extraction

[0051] The texture of the flame image is irregular, and we calculate the texture features through the gray level co-occurrence matrix (GLCM). The specific texture feature indicators include contrast, energy, homogeneity and correlation, which are defined as:

[0052]

[0053] Among them, P(i,j) is the element in the gray level co-occurrence matrix, μ i ,μ j is the mean of the row and column, σ i ,σ j is the standard deviation. Experiments show that flame images have higher contrast and energy, but lower homogeneity, showing more dramatic texture changes.

[0054] (3) SIFT feature extraction

[0055] Scale-invariant feature transform (SIFT) is used to extract local key points in an image, and is particularly suitable for images with complex edges such as flames. The key steps of SIFT features include:

[0056] Gaussian difference pyramid construction:

[0057] D(x,y,σ)=L(x,y,kσ)-L(x,y,σ)

[0058] Among them, L(x, y, σ) is the Gaussian blurred image of the image at scale σ, and k is the scale space interval factor.

[0059] Key point detection: The key points are obtained by performing local extrema detection on the Gaussian difference image D(x, y, σ).

[0060] Direction assignment: Assign a direction to each key point to form an invariant feature vector.

[0061] 2. Feature fusion and weight allocation

[0062] After feature extraction, we use the multi-feature fusion weighted random forest (MFFRW) algorithm to perform feature fusion. Specifically, the weight w of different features in the final classification is determined by their performance in the classification process, and the formula is as follows:

[0063] F fusion =w color F color +w texture F texture +w SIFT F SIFT

[0064] Among them, F color 、F texture 、F SIFT They are the classification results of color, texture and SIFT features respectively, and the weight w is determined by the accuracy of each feature in the training set:

[0065]

[0066] Through experiments, we found that:

[0067] Color feature weight w color =0.40

[0068] Texture feature weight w texture =0.35

[0069] SIFT feature weight w SIFT =0.25

[0070] 3. Support Vector Machine Classifier (SVM)

[0071] The final classification is achieved through support vector machine (SVM). The core goal of SVM is to classify by finding the hyperplane that maximizes the distance between classes. We use the kernel function with radial basis function (RBF), and the objective function of the model is:

[0072]

[0073] The constraints are:

[0074] y i (w*φ(x i )+b)>1-ξ i ,ξ i >0

[0075] Where w is the normal vector of the decision hyperplane, ξ i is the slack variable, C is the penalty parameter, φ(x i ) is the kernel function, which maps the input data to a high-dimensional space.

[0076] The C and γ values ​​were optimized by grid search method, and the optimal parameter combination C=1.0, γ=0.1 was obtained.

[0077] 4. Performance Evaluation and Results

[0078] After multiple experiments and optimizations, the system achieved the following performance indicators on the flame image recognition task:

[0079] Accuracy: 97.5%

[0080] False Positive Rate (FPR): 2.3%

[0081] False Negative Rate (FNR): 1.8%;

[0082] The final classification decision function of SVM is:

[0083]

[0084] Among them, αi is the Lagrange multiplier, y i is the label, K(x i ,x) is the kernel function.

[0085] Through this multi-feature fusion advanced algorithm design and optimization, the fire detection system performs well in flame recognition in complex environments, and can effectively identify fires and avoid common interference factors.

[0086] Kalman filter algorithm: For a running electrical device, its temperature will increase with the increase of running time. At the same time, the data collected by the temperature sensor may have certain measurement noise. The Kalman filter algorithm can accurately estimate the current temperature state of the device based on the initial temperature of the device, running time and data collected by the temperature sensor.

[0087] The specific implementation of the algorithm is as follows:

[0088] System state equation and measurement equation:

[0089] (1) System state equation: For temperature monitoring of electrical equipment, assuming that the temperature of the equipment is the system state variable, its state equation can be expressed as:

[0090] x k =x k-1 +v k-1

[0091] where x k is the temperature of the device at time k, x k-1 is the temperature of the device at time k-1, v k-1 It is the process noise of the system, which reflects other uncertain factors in the process of equipment temperature change except the linear increase with time (such as the impact of ambient temperature change on equipment heat dissipation, etc.).

[0092] Measurement equation: The measurement equation represents the relationship between the measured value and the system state. Assume that the measured value of the temperature sensor is z, and the measurement equation is:

[0093] z k =x k +w k

[0094] where z k is the measured value of the temperature sensor at time k, w k It is the measurement noise, which reflects the error of the temperature sensor itself and the uncertainty caused by factors such as the measurement environment.

[0095] Prediction Steps:

[0096] In Kalman filtering, each step first makes a prediction. According to the state equation, the predicted value of the device temperature at time k is (The superscript “-” indicates a predicted value) The optimal estimated value of the device temperature at time k-1 can be obtained To calculate:

[0097]

[0098] At the same time, the covariance of the predicted values ​​needs to be calculated (The covariance reflects the uncertainty of the estimated value, which can be obtained by the covariance P of the optimal estimated value at time k-1 k-1 And process noise covariance Q (covariance matrix of process noise, its value needs to be set according to actual situation) to calculate:

[0099]

[0100] Update steps:

[0101] (1) Calculate the Kalman gain K based on the measurement equation and the predicted value k , which is a coefficient that weighs the weight of the predicted value and the measured value:

[0102]

[0103] Where R is the measurement noise covariance (the covariance matrix of the measurement noise w, which needs to be set according to the actual situation).

[0104] (2) Calculate the optimal estimate of the device temperature at time k based on the Kalman gain, predicted value, and measured value

[0105]

[0106] , update the covariance P of the optimal estimate k :

[0107]

[0108] Performance evaluation indicators:

[0109] Mean square error (MSE): Mean square error is a common indicator to measure the average deviation between the estimated value and the true value. For the device temperature estimation problem, calculate the estimated temperature at each time point With the real temperature x k (The actual temperature is difficult to obtain, but it can be verified at some time points by high-precision reference measurement equipment) The square of the difference is then averaged, and the formula is:

[0110]

[0111] Where N is the total number of times. The smaller the MSE, the better the estimation effect of the Kalman filter algorithm, that is, the smaller the deviation between the estimated temperature and the actual temperature.

[0112] Mean absolute error (MAE): The mean absolute error is another measure of estimation error. It calculates the estimated temperature at each time point. The difference from the actual temperature x k The average of the absolute values ​​of . The formula is:

[0113]

[0114] Similar to MSE, the smaller the MAE, the higher the estimation accuracy of the algorithm, which directly reflects the average absolute deviation between the estimated value and the true value.

[0115] Convergence speed: Convergence speed refers to the number of time steps it takes for the algorithm to reach a relatively stable estimated state from the initial state. This can be judged by observing the curve of the estimated temperature value changing over time. When the curve tends to be stable, that is, the estimated temperature changes at adjacent time points are very small, the algorithm is considered to have converged.

[0116] For example, in the experiment, the temperature of the electrical equipment was monitored at 100 time points, with a time interval of 1 minute, an initial temperature of 30°C, and the equipment temperature increased roughly linearly with the running time, with an average increase of 2°C every 10 minutes (this is just a simplified model). At the same time, the process noise covariance Q = 0.01 and the measurement noise covariance R = 0.1. The data collected by the temperature sensor is based on the addition of random noise that meets the above noise characteristics.

[0117] Finally, the average value of the results obtained from multiple tests is:

[0118] Mean square error (MSE): 0.25;

[0119] Mean absolute error (MAE): 0.4;

[0120] Convergence speed: 20-30 time points to reach convergence state;

[0121] In this embodiment, a real-time monitoring device for a meter box is also provided. The system is configured to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" is a combination of software and / or hardware that can implement a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0122] Figure 2 is a structural block diagram of a real-time monitoring device for a meter box according to one embodiment of the present invention. Figure 2 As shown, a real-time monitoring device for a meter box is used as an example, including: a multimodal data acquisition module, used to collect multimodal data; a control module, connected to the multimodal data acquisition module, and the control module is used to control the multimodal data acquisition module; a communication module, connected to the multimodal data acquisition module and to a server, the communication module is used to realize communication between the control module and the server, and the server is used to interact with monitoring personnel.

[0123] Optionally, the multimodal data acquisition module includes a smoke sensor, an infrared sensor, a radar sensor, a temperature and humidity sensor, a water immersion sensor, a camera, an ultrasonic sensor, an acoustic and optical sensor, and a positioning module.

[0124] Specifically, a multimodal real-time monitoring device for a meter box is installed inside the meter box. The overall mechanical structure has a fire-proof design and is composed of a smoke sensor module, an infrared sensor module, a radar sensor module, a temperature and humidity sensor module, a water immersion sensor module, a camera module, an ultrasonic module, an acoustic and optical module, an embedded control module, a power module, a communication module, a positioning module, a background server module, and a mechanical structure module.

[0125] Functions of each module of the device:

[0126] (1) When the smoke sensor module detects fire smoke, it sends it to the embedded control module; the embedded control module analyzes the smoke data to determine the fire smoke situation. If yes, it starts the camera module. The embedded control module performs motion detection and edge detection on the flame visual image data, analyzes the flame and smoke characteristics, and introduces image recognition and reconstruction tasks to assist model training, reduce the model's dependence on label data, improve detection accuracy and response speed, and determine whether a fire has occurred. If a fire is confirmed, the sound and light module is triggered immediately, with a sound reminder and a flashing light warning.

[0127] (2) When the radar sensing sensor and the infrared sensing sensor dynamically and in real time monitor the small animals near the electric meter box, an early warning is triggered and sent to the embedded control module; the embedded control module controls the camera module to take pictures; the embedded control module controls the ultrasonic module to emit a sound of a specific frequency to drive the small animals away from the electric meter box.

[0128] (3) When the infrared sensor module detects that the electricity thief is forcing the meter box to open, it triggers an early warning and sends it to the embedded control module; the embedded control module controls the camera module to take pictures, consolidate the evidence, and ensure the reliability of data collection and the timeliness of supervision.

[0129] (4) The embedded control module is connected to the communication module to send the location information and warning information (such as fire, small animal intrusion, and electricity theft) of the positioning module to the staff, who can respond quickly and arrange relevant emergency work to prevent the expansion of power outage accidents. The power module has battery energy storage. If a fire causes a power outage, the battery can last for a period of time to ensure that the intelligent device continues to work and continue to monitor the development of the fire in real time. If electricity theft occurs, the evidence is confirmed as soon as possible to deter the theft.

[0130] like Figure 3As shown, the hardware structure is as follows: infrared sensor module, select input level: 3.3~5V, communication mode: IO. Smoke sensor module, select MAX30105, input level: 5V, communication protocol: IIC communication. Radar sensor module selects input level: 5V, communication protocol: IO or serial communication. Temperature and humidity sensor module selects input level: 3.3V, communication protocol: serial communication. Water sensor module selects input level: 3.3V~5V, communication mode: IO / AD. Ultrasonic module, power amplifier function, input voltage: 12~24V. Sound and light module, green LED and red LED: green light system is normally on, otherwise it goes out; red light flashes when a fire is detected, otherwise it goes out. Passive buzzer: emits a sound prompt when a fire is detected. Communication module, select support for 4G+SMS+GPS function, communication mode: 485. The main control module selects the STM32407 system, which has an OV2640 module, a camera module interface, and a TF card interface, which is convenient for connecting to the camera module. At the same time, the FATFS file system is used to manage the SD card. As shown in Table 1, the IO port requirements of the STM32407 system.

[0131] Table 1 STM32407 system IO port requirements

[0132]

[0133]

[0134] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0135] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the real-time monitoring method for a meter box described in any of the above embodiments.

[0136] Optionally, in this embodiment, the processor in the above electronic device may be configured to run a computer program to perform the following steps:

[0137] Step S101, performing round-robin detection on the multimodal data collected by the multimodal data collection module to obtain a detection result.

[0138] Step S102: in response to the detection result indicating that the multimodal data is abnormal, the abnormality is handled according to a preset abnormality handling strategy.

[0139] Optionally, in response to the detection result indicating that there is an abnormality in the multimodal data, exception handling is performed according to a preset exception handling strategy, including: in response to the detection result indicating that there is an abnormality in the photoelectric sensing switch data, based on the preset exception handling strategy, controlling the camera to turn on and acquire image data, and at the same time controlling the indicator light to change color, wherein the photoelectric sensing switch data is included in the multimodal data.

[0140] Optionally, in response to the detection result indicating that the multimodal data has an abnormality, the exception is handled according to a preset exception handling strategy, including: in response to the detection result indicating that the millimeter-wave sensing radar data has an abnormality, based on the preset exception handling strategy, starting the sound and light alarm module and the ultrasonic expulsion device, and controlling the indicator light to change color, wherein the millimeter-wave sensing radar data is included in the multimodal data.

[0141] Optionally, the fault is handled according to a preset strategy, including: in response to the detection results indicating that there are abnormalities in the temperature and humidity sensor data, water immersion sensor data, and smoke sensor data, based on a preset abnormality handling strategy, controlling the indicator light to change color, wherein the temperature and humidity sensor data, water immersion sensor data, and smoke sensor data are included in the multimodal data.

[0142] Optionally, the real-time monitoring method for the meter box also includes: extracting features from the image data to obtain feature data; and determining an image recognition result based on the feature data using a preset image recognition model, wherein the image recognition result is used to determine whether a fire exists.

[0143] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0144] An embodiment of the present invention further provides a non-volatile storage medium, in which a computer program is stored, wherein the computer program is configured to execute the real-time monitoring method for a meter box described in any of the above embodiments when running on a computer or a processor.

[0145] Optionally, in this embodiment, the computer program may be configured to store a computer program configured to perform the following steps:

[0146] Step S101, performing round-robin detection on the multimodal data collected by the multimodal data collection module to obtain a detection result.

[0147] Step S102: in response to the detection result indicating that the multimodal data is abnormal, the abnormality is handled according to a preset abnormality handling strategy.

[0148] Optionally, in response to the detection result indicating that there is an abnormality in the multimodal data, exception handling is performed according to a preset exception handling strategy, including: in response to the detection result indicating that there is an abnormality in the photoelectric sensing switch data, based on the preset exception handling strategy, controlling the camera to turn on and acquire image data, and at the same time controlling the indicator light to change color, wherein the photoelectric sensing switch data is included in the multimodal data.

[0149] Optionally, in response to the detection result indicating that the multimodal data has an abnormality, the exception is handled according to a preset exception handling strategy, including: in response to the detection result indicating that the millimeter-wave sensing radar data has an abnormality, based on the preset exception handling strategy, starting the sound and light alarm module and the ultrasonic expulsion device, and controlling the indicator light to change color, wherein the millimeter-wave sensing radar data is included in the multimodal data.

[0150] Optionally, the fault is handled according to a preset strategy, including: in response to the detection results indicating that there are abnormalities in the temperature and humidity sensor data, water immersion sensor data, and smoke sensor data, based on a preset abnormality handling strategy, controlling the indicator light to change color, wherein the temperature and humidity sensor data, water immersion sensor data, and smoke sensor data are included in the multimodal data.

[0151] Optionally, the real-time monitoring method for the meter box also includes: extracting features from the image data to obtain feature data; and determining an image recognition result based on the feature data using a preset image recognition model, wherein the image recognition result is used to determine whether a fire exists.

[0152] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0153] An embodiment of the present invention further provides a computer program product, including a computer program, which implements the real-time monitoring method for a meter box described in any of the above embodiments when executed by a processor.

[0154] Optionally, in this embodiment, the above computer program implements the following steps when executed by a processor:

[0155] Step S101, performing round-robin detection on the multimodal data collected by the multimodal data collection module to obtain a detection result.

[0156] Step S102: in response to the detection result indicating that the multimodal data is abnormal, the abnormality is handled according to a preset abnormality handling strategy.

[0157] Optionally, in response to the detection result indicating that there is an abnormality in the multimodal data, exception handling is performed according to a preset exception handling strategy, including: in response to the detection result indicating that there is an abnormality in the photoelectric sensing switch data, based on the preset exception handling strategy, controlling the camera to turn on and acquire image data, and at the same time controlling the indicator light to change color, wherein the photoelectric sensing switch data is included in the multimodal data.

[0158] Optionally, in response to the detection result indicating that the multimodal data has an abnormality, the exception is handled according to a preset exception handling strategy, including: in response to the detection result indicating that the millimeter-wave sensing radar data has an abnormality, based on the preset exception handling strategy, starting the sound and light alarm module and the ultrasonic expulsion device, and controlling the indicator light to change color, wherein the millimeter-wave sensing radar data is included in the multimodal data.

[0159] Optionally, the fault is handled according to a preset strategy, including: in response to the detection results indicating that there are abnormalities in the temperature and humidity sensor data, water immersion sensor data, and smoke sensor data, based on a preset abnormality handling strategy, controlling the indicator light to change color, wherein the temperature and humidity sensor data, water immersion sensor data, and smoke sensor data are included in the multimodal data.

[0160] Optionally, the real-time monitoring method for the meter box also includes: extracting features from the image data to obtain feature data; and determining an image recognition result based on the feature data using a preset image recognition model, wherein the image recognition result is used to determine whether a fire exists.

[0161] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0162] In some embodiments provided in the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the modules can be a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, modules or indirect coupling or communication connection of modules, which can be electrical or other forms.

[0163] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0164] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of software functional modules.

[0165] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0166] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A real-time monitoring method for a meter box, characterized in that: include: Performing round-robin testing on the multimodal data collected by the multimodal data collection module to obtain a test result; In response to the detection result indicating that the multimodal data is abnormal, the exception is handled according to a preset exception handling strategy.

2. The real-time monitoring method of a meter box according to claim 1, characterized in that: In response to the detection result indicating that the multimodal data is abnormal, performing abnormal processing according to a preset abnormal processing strategy includes: In response to the detection result indicating that there is an abnormality in the photoelectric sensor switch data, based on the preset abnormality handling strategy, the camera is controlled to turn on and acquire image data, and the indicator light is controlled to change color, wherein the photoelectric sensor switch data is included in the multimodal data.

3. The real-time monitoring method of a meter box according to claim 1, characterized in that: In response to the detection result indicating that the multimodal data is abnormal, performing abnormal processing according to a preset abnormal processing strategy includes: In response to the detection result indicating that there is an abnormality in the millimeter-wave sensing radar data, based on the preset abnormality handling strategy, the sound and light alarm module and the ultrasonic expulsion device are started, and the indicator light is controlled to change color, wherein the millimeter-wave sensing radar data is included in the multimodal data.

4. The real-time monitoring method of a meter box according to claim 1, characterized in that: The processing of the fault according to the preset strategy includes: In response to the detection results indicating that there are abnormalities in the temperature and humidity sensor data, the water immersion sensor data, and the smoke sensor data, based on the preset abnormality handling strategy, the indicator light is controlled to change color, wherein the temperature and humidity sensor data, the water immersion sensor data, and the smoke sensor data are included in the multimodal data.

5. The real-time monitoring method of a meter box according to claim 2, characterized in that: Also includes: Extracting features from the image data to obtain feature data; Based on the feature data, an image recognition result is determined using a preset image recognition model, wherein the image recognition result is used to determine whether a fire exists.

6. A real-time monitoring device for a meter box, characterized in that: include: A multimodal data acquisition module, used for acquiring multimodal data; A control module connected to the multimodal data acquisition module, the control module being used to control the multimodal data acquisition module; A communication module is connected to the multimodal data acquisition module and the server, and the communication module is used to realize the communication between the control module and the server, and the server is used to interact with the monitoring personnel.

7. The real-time monitoring device for a meter box according to claim 6, characterized in that: The multimodal data acquisition module includes a smoke sensor, an infrared sensor, a radar sensor, a temperature and humidity sensor, a water immersion sensor, a camera, an ultrasonic sensor, an acoustic and optical sensor, and a positioning module.

8. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the meter box real-time monitoring method as described in any one of claims 1 to 5 above.

9. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a computer program, wherein the computer program is configured to execute the meter box real-time monitoring method described in any one of claims 1 to 5 when running on a computer or a processor.

10. A computer program product, characterized in that It comprises a computer program, which, when executed by a processor, implements the real-time monitoring method for a meter box according to any one of claims 1 to 5.

Images