Equipment parameter monitoring and early warning method and device, equipment and storage medium
The method enhances instrument landing system monitoring by correlating parameters through text recognition and history curve analysis, enabling accurate predictive maintenance.
Patent Information
- Application Number
- CN202411182574.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-12-06
AI Technical Summary
Existing instrument landing system monitoring software lacks correlation between parameters, fails to provide historical data, and relies solely on current status for maintenance decisions, making accurate predictions impossible.
A method involving parameter page image acquisition, text segmentation, and recognition using CRNN and FCN networks to generate a parameter history curve, with abnormal jitter triggering early warnings.
Enables predictive monitoring and early warning of equipment parameters, improving maintenance accuracy by capturing parameter jitter and generating timely alerts.
Smart Images

Figure CN119091428A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data analysis technology, and in particular to a method, device, equipment and storage medium for monitoring and warning equipment parameters. Background Art
[0002] Instrument landing equipment is an important device that provides navigation information for aircraft. It is one of the five key devices. The equipment integrity rate is extremely important for air traffic control. In order to ensure the equipment integrity rate, it is necessary to determine whether the equipment has failed based on the equipment monitoring parameters and take corresponding repair and maintenance measures. Currently, several commonly used instrument landing systems are equipped with equipment monitoring software, which displays various equipment parameters in real time for maintenance personnel to observe the equipment status. However, the monitoring software that comes with the instrument landing equipment only displays the current status of the system. The correlation between the displayed parameters is weak, and it is impossible to obtain equipment historical data and predict changes in system parameters. Based on the insufficient information available to maintenance personnel, it is impossible to make a more accurate judgment on the equipment status.
[0003] In summary, the problems existing in the prior art need to be solved urgently. Summary of the invention
[0004] The present invention provides a monitoring and early warning method, device, equipment and storage medium for equipment parameters, which are used to solve the defects in the prior art and realize predictive monitoring and early warning of equipment parameters.
[0005] The present invention provides a device parameter monitoring and early warning method, comprising:
[0006] Acquire a parameter page image of a target monitoring device, wherein the parameter page image includes device parameter information;
[0007] Select the parameter page image to obtain a parameter text area containing the device parameter information;
[0008] Recognize the parameter text area by using a text recognition model to obtain parameter text information of the device parameter information;
[0009] Determining a parameter history curve of the target monitoring device according to the parameter text information;
[0010] When the parameter history curve has abnormal jitter, an early warning message is generated.
[0011] According to a device parameter monitoring and early warning method provided by the present invention, the step of obtaining a parameter page image of a target monitoring device specifically includes:
[0012] Obtaining the monitoring page video of the target monitoring device;
[0013] Convert the monitoring page video into a video stream digital signal through an encoder, and send the digital signal to a server;
[0014] The parameter page image of the target monitoring device is intercepted from the video stream digital signal through the server.
[0015] According to a device parameter monitoring and early warning method provided by the present invention, the step of selecting the parameter page image to obtain a parameter text area containing the device parameter information specifically includes:
[0016] Perform DB text segmentation on the parameter page image to obtain a binary prediction image of the parameter page image, wherein the binary prediction image includes text pixels and non-text pixels;
[0017] Continuous text pixels are connected into the parameter text area.
[0018] According to a device parameter monitoring and early warning method provided by the present invention, the text recognition model specifically includes: a CRNN network and a FCN network.
[0019] According to a device parameter monitoring and early warning method provided by the present invention, after the step of determining the parameter history curve of the target monitoring device according to the parameter text information, the method further includes:
[0020] Extracting parameter values and timestamps from the parameter text information;
[0021] The parameter values and corresponding timestamps are stored as parameter sequence data.
[0022] According to a device parameter monitoring and early warning method provided by the present invention, the step of determining the parameter history curve of the target monitoring device according to the parameter text information specifically includes:
[0023] According to the first sliding window and the second sliding window, respectively, the parameter text information is subjected to sliding average processing to obtain a first sliding average sequence and a second sliding average sequence, wherein the parameter text information includes a parameter value and a timestamp;
[0024] Calculating a target sliding average sequence according to the first sliding average sequence and the second sliding average sequence;
[0025] The parameter history curve is determined according to the difference between the parameter sequence data and the target sliding average sequence.
[0026] According to a device parameter monitoring and early warning method provided by the present invention, the parameters in the target sliding average sequence are obtained by the following formula:
[0027]
[0028] Among them, MA i is the i-th parameter in the sequence, k is the sliding window size,
[0029] The present invention also provides a method, device, equipment and storage medium for monitoring and warning equipment parameters, including:
[0030] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a monitoring and early warning method for device parameters as described above is implemented.
[0031] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the monitoring and early warning method of the device parameters as described in any one of the above is implemented.
[0032] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the monitoring and early warning method of the device parameters as described above is implemented.
[0033] The device parameter monitoring and early warning method, apparatus, device and storage medium provided by the present invention obtain a parameter page image of a target monitoring device, wherein the parameter page image includes device parameter information; the parameter page image is framed to obtain a parameter text area containing the device parameter information; the parameter text area is identified by a text recognition model to obtain parameter text information of the device parameter information; a parameter history curve of the target monitoring device is determined based on the parameter text information; and when the parameter history curve has abnormal jitter, an early warning message is generated. The present invention can capture parameter jitter based on the parameter page image of the target monitoring device and draw a parameter history curve, thereby realizing the prediction of the operating status of the target monitoring device and achieving the effect of early warning. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0035] Figure 1 It is a flow chart of the monitoring and early warning method of equipment parameters provided by the present invention;
[0036] Figure 2It is a structural schematic diagram of the monitoring and early warning device for equipment parameters provided by the present invention;
[0037] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION
[0038] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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 are within the scope of protection of the present invention.
[0039] Instrument Landing System (ILS) is an important device that provides navigation information for aircraft and is one of the five key aviation navigation equipment. The integrity of the equipment directly affects the efficiency and safety of air traffic control. Therefore, ensuring the normal operation of instrument landing equipment is crucial to aviation safety.
[0040] At present, the instrument landing system is equipped with equipment monitoring software, which can display various parameters of the equipment in real time for maintenance personnel to observe and analyze the equipment status. However, the existing monitoring software has the following shortcomings:
[0041] Weak parameter correlation: The monitoring software only displays the current device status and lacks analysis of the correlation between various parameters.
[0042] Lack of historical data: It is impossible to obtain historical data of the equipment, making it difficult to conduct analysis and prediction based on long-term data.
[0043] Insufficient information: Maintenance personnel can only make judgments based on the currently displayed information, making it difficult to make accurate predictions and maintenance decisions about equipment status.
[0044] In order to solve the problems in the prior art, the present invention proposes a monitoring and early warning method for equipment parameters to achieve predictive monitoring and early warning of equipment parameters. The monitoring and early warning method for equipment parameters is described below. Figure 1 As shown, including but not limited to the following steps:
[0045] Step 110: Acquire a parameter page image of a target monitoring device, wherein the parameter page image includes device parameter information.
[0046] In step 110, the parameter page image of the target monitoring device can be obtained by using an encoder, a KVM network or a camera. Specifically, the encoder: connects to the monitoring device and captures the device screen image in real time. The KVM network: captures the screen image of the current parameter page of the device through the remote control system. The camera: points the camera at the device display screen to capture the parameter page image.
[0047] Among them, the parameter page image should contain various operating parameter information of the equipment to ensure that the image is clear and unobstructed to facilitate subsequent processing.
[0048] Step 120: select the parameter page image to obtain a parameter text area containing the device parameter information.
[0049] In step 120, after obtaining the parameter page image, the DB (Differentiation Binarization) text segmentation algorithm can be used to process the image. Specifically, the pre-trained DB text segmentation model is used to perform pixel-level binary prediction on the parameter page image. According to the prediction results, a post-processing algorithm (such as threshold segmentation, contour detection, etc.) is applied to generate a bounding box containing device parameter information. The parameter text area containing the device parameter information in the image is selected. Through this step, the position of the device parameters in the image can be accurately located, laying the foundation for subsequent text recognition.
[0050] Step 130: Identify the parameter text area using a text recognition model to obtain parameter text information of the device parameter information.
[0051] In step 130, the selected parameter text area is subjected to text recognition using a CRNN (Convolutional Recurrent Neural Network) network and a FCN (Fully Convolutional Network) network based on CTC (Connection Temporal Classification). Specifically, the parameter text area image is input into the CRNN network, the spatial features are extracted through the convolution layer, the sequence information is captured through the recursive layer, and finally the text sequence is obtained by CTC decoding. The parameter text area image is input into the FCN network, and the pixel-level text area prediction is achieved through the full convolution layer to further improve the recognition accuracy. Combining the recognition results of the two models, the parameter text containing the device parameter information is obtained.
[0052] Step 140: Determine a parameter history curve of the target monitoring device according to the parameter text information.
[0053] The device parameter information identified in step 130 is converted into time series data, and each parameter value and its corresponding timestamp are recorded. Specifically, the parameter text information is stored as data points in chronological order to form parameter history data. The sliding average window method is applied to smooth the history data. Windows of different lengths are set to calculate the sliding average sequences of short and long periods. The parameter jitter curve is generated by calculating the difference between the original parameter sequence and the sliding average sequence.
[0054] Step 150: When the parameter history curve has abnormal jitter, generate warning information.
[0055] In step 150, the generated parameter jitter curve is monitored and analyzed to determine whether there is abnormal fluctuation. Specifically, the jitter threshold is set: according to the operating characteristics of the equipment, a reasonable jitter threshold range is set. Subsequently, the jitter curve is monitored in real time, and the short-period and long-period jitter curves are analyzed in real time. When the jitter curve exceeds the set threshold range, it is judged as abnormal jitter. Subsequently, an early warning message is generated. Once abnormal jitter is detected, an early warning message is immediately generated and sent to maintenance personnel so that timely measures can be taken to prevent equipment failure.
[0056] The device parameter monitoring and early warning method provided by the present invention obtains a parameter page image of a target monitoring device, wherein the parameter page image includes device parameter information; the parameter page image is framed to obtain a parameter text area containing the device parameter information; the parameter text area is recognized by a text recognition model to obtain parameter text information of the device parameter information; a parameter history curve of the target monitoring device is determined based on the parameter text information; and when the parameter history curve has abnormal jitter, an early warning message is generated. The present invention can capture parameter jitter based on the parameter page image of the target monitoring device and draw a parameter history curve, thereby realizing the prediction of the operating status of the target monitoring device and achieving the effect of early warning.
[0057] As a further embodiment, the step of obtaining the parameter page image of the target monitoring device specifically includes:
[0058] Obtaining the monitoring page video of the target monitoring device;
[0059] Convert the monitoring page video into a video stream digital signal through an encoder, and send the digital signal to a server;
[0060] The parameter page image of the target monitoring device is intercepted from the video stream digital signal through the server.
[0061] In this example, it is necessary to obtain the parameter page image. You can use a camera to aim at the display screen of the target monitoring device to record the monitoring page video of the device in real time. Use a video encoder to convert the monitoring page video captured by the camera into a digital signal. The encoder can compress the video signal into a standard video format (such as H.264). Transmit the encoded video stream digital signal to the server through the network to ensure the real-time and stability of the video stream. After receiving the video stream, the server parses the video stream digital signal in real time and extracts the key frames. In the extracted key frames, further processing is performed through image processing technology (such as image enhancement, noise filtering, etc.) to obtain a clear parameter page image. According to the preset time interval or trigger condition, the parameter page image is periodically intercepted from the video stream to ensure that the image update frequency meets the actual needs.
[0062] As a further embodiment, the step of selecting the parameter page image to obtain a parameter text area containing the device parameter information specifically includes:
[0063] Perform DB text segmentation on the parameter page image to obtain a binary prediction image of the parameter page image, wherein the binary prediction image includes text pixels and non-text pixels;
[0064] Continuous text pixels are connected into the parameter text area.
[0065] In the present embodiment, it is necessary to use the DB (Differentiable Binariization) text segmentation model of pre-training to predict the parameter page image at pixel level. The DB text segmentation model can effectively distinguish text pixels and non-text pixels, and generate a binary prediction map, in which text pixels are marked as 1 and non-text pixels are marked as 0. In the binary prediction map, text pixels are connected by morphological operations (such as expansion and corrosion) to form a complete text area. Use contour detection algorithm (such as findContours function in OpenCV) to detect the continuous text pixel area in the binary prediction map. Detected contour is further processed (such as removing noise, merging adjacent text areas, etc.), and finally obtains the bounding box of the parameter text area.
[0066] As a further embodiment, the text recognition model specifically includes: a CRNN network and a FCN network.
[0067] Specifically, the parameter text region image is input into a pre-trained CNN model (such as VGG, ResNet) to extract high-dimensional features. The extracted feature sequence is input into a bidirectional LSTM (Long Short-Term Memory) network to capture the contextual information in the sequence. The output of the LSTM is converted into a text sequence using a CTC decoder. Next, the parameter text region image is input into a pre-trained FCN model to generate pixel-level classification results. The pixel-level classification results are synthesized into a complete text sequence through post-processing methods (such as connected domain analysis, NMS (Non-Maximum Suppression), etc.).
[0068] As a further embodiment, after the step of determining the parameter history curve of the target monitoring device according to the parameter text information, the method further includes:
[0069] Extracting parameter values and timestamps from the parameter text information;
[0070] The parameter values and corresponding timestamps are stored as parameter sequence data.
[0071] Specifically, the identified parameter text information is parsed to extract the parameter value and the corresponding timestamp. For example, the parameter text information may include multiple data items, each of which contains a parameter value and a timestamp. The extracted parameter value and timestamp are then stored in a database or file system in the form of a key-value pair to form complete parameter sequence data. These data will serve as the basis for subsequent analysis and processing, and provide raw data support for determining the parameter history curve.
[0072] As a further embodiment, the step of determining the parameter history curve of the target monitoring device according to the parameter text information specifically includes:
[0073] According to the first sliding window and the second sliding window, respectively, the parameter text information is subjected to sliding average processing to obtain a first sliding average sequence and a second sliding average sequence, wherein the parameter text information includes a parameter value and a timestamp;
[0074] Calculating a target sliding average sequence according to the first sliding average sequence and the second sliding average sequence;
[0075] The parameter history curve is determined according to the difference between the parameter sequence data and the target sliding average sequence.
[0076] As a further embodiment, the parameters in the target sliding average sequence are obtained by the following formula:
[0077]
[0078] Among them, MA i is the i-th parameter in the sequence, k is the sliding window size,
[0079] The parameter sequence after sliding average is divided into two short-period sequences and two long-period sequences according to the size of the sliding window. The difference between any sequence and the original parameter sequence can obtain the corresponding jitter curve. The difference between two short-period sequences can obtain the short-period jitter curve, and the difference between two long-period sequences can obtain the long-period jitter curve.
[0080] The monitoring and early warning device for equipment parameters provided by the present invention is described below. Figure 2 As shown, the device for monitoring and warning equipment parameters described below and the method for monitoring and warning equipment parameters described above can refer to each other.
[0081] A monitoring and early warning device for equipment parameters, comprising:
[0082] An image acquisition module 210 is used to acquire a parameter page image of a target monitoring device, wherein the parameter page image includes device parameter information;
[0083] An area selection module 220 is used to select the parameter page image to obtain a parameter text area containing the device parameter information;
[0084] A text recognition module 230 is used to recognize the parameter text area through a text recognition model to obtain parameter text information of the device parameter information;
[0085] A curve determination module 240, configured to determine a parameter history curve of the target monitoring device according to the parameter text information;
[0086] The warning generation module 250 is used to generate warning information when there is abnormal jitter in the parameter history curve.
[0087] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3 As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the device parameter monitoring and early warning method, which includes:
[0088] Acquire a parameter page image of a target monitoring device, wherein the parameter page image includes device parameter information;
[0089] Select the parameter page image to obtain a parameter text area containing the device parameter information;
[0090] Recognize the parameter text area by using a text recognition model to obtain parameter text information of the device parameter information;
[0091] Determining a parameter history curve of the target monitoring device according to the parameter text information;
[0092] When the parameter history curve has abnormal jitter, an early warning message is generated.
[0093] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several 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: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM, Read-On l yMemory), a random access memory (RAM, Random Access Memory), a disk or an optical disk.
[0094] On the other hand, the present invention further provides a computer program product, the computer program product includes a computer program, the computer program can be stored in a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the device parameter monitoring and early warning method provided by the above methods, the method includes:
[0095] Acquire a parameter page image of a target monitoring device, wherein the parameter page image includes device parameter information;
[0096] Select the parameter page image to obtain a parameter text area containing the device parameter information;
[0097] Recognize the parameter text area by using a text recognition model to obtain parameter text information of the device parameter information;
[0098] Determining a parameter history curve of the target monitoring device according to the parameter text information;
[0099] When the parameter history curve has abnormal jitter, an early warning message is generated.
[0100] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform the device parameter monitoring and early warning method provided by the above methods, the method comprising:
[0101] Acquire a parameter page image of a target monitoring device, wherein the parameter page image includes device parameter information;
[0102] Select the parameter page image to obtain a parameter text area containing the device parameter information;
[0103] Recognize the parameter text area by using a text recognition model to obtain parameter text information of the device parameter information;
[0104] Determining a parameter history curve of the target monitoring device according to the parameter text information;
[0105] When the parameter history curve has abnormal jitter, an early warning message is generated.
[0106] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0107] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0108] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for monitoring and early warning of equipment parameters, characterized in that: include: Acquire a parameter page image of a target monitoring device, wherein the parameter page image includes device parameter information; Select the parameter page image to obtain a parameter text area containing the device parameter information; Recognize the parameter text area by using a text recognition model to obtain parameter text information of the device parameter information; Determining a parameter history curve of the target monitoring device according to the parameter text information; When the parameter history curve has abnormal jitter, an early warning message is generated.
2. The device parameter monitoring and early warning method according to claim 1 is characterized in that: The step of obtaining the parameter page image of the target monitoring device specifically includes: Obtaining the monitoring page video of the target monitoring device; Convert the monitoring page video into a video stream digital signal through an encoder, and send the digital signal to a server; The parameter page image of the target monitoring device is intercepted in the video stream digital signal through the server.
3. The device parameter monitoring and early warning method according to claim 1 is characterized in that: The step of selecting the parameter page image to obtain a parameter text area containing the device parameter information specifically includes: Perform DB text segmentation on the parameter page image to obtain a binary prediction image of the parameter page image, wherein the binary prediction image includes text pixels and non-text pixels; Continuous text pixels are connected into the parameter text area.
4. The device parameter monitoring and early warning method according to claim 1 is characterized in that: The text recognition model specifically includes: a CRNN network and a FCN network.
5. The device parameter monitoring and early warning method according to claim 1 is characterized in that: After the step of determining the parameter history curve of the target monitoring device according to the parameter text information, the method further includes: Extracting parameter values and timestamps from the parameter text information; The parameter values and corresponding timestamps are stored as parameter sequence data.
6. The device parameter monitoring and early warning method according to claim 5 is characterized in that: The step of determining the parameter history curve of the target monitoring device according to the parameter text information specifically includes: According to the first sliding window and the second sliding window, respectively, the parameter text information is subjected to sliding average processing to obtain a first sliding average sequence and a second sliding average sequence, wherein the parameter text information includes a parameter value and a timestamp; Calculating a target sliding average sequence according to the first sliding average sequence and the second sliding average sequence; The parameter history curve is determined according to the difference between the parameter sequence data and the target sliding average sequence.
7. The device parameter monitoring and early warning method according to claim 6 is characterized in that: The parameters in the target sliding average sequence are obtained by the following formula: Among them, MA i is the i-th parameter in the sequence, and k is the sliding window size.
8. A monitoring and early warning device for equipment parameters, characterized in that: include: An image acquisition module, used to acquire a parameter page image of a target monitoring device, wherein the parameter page image includes device parameter information; An area selection module is used to select the parameter page image to obtain a parameter text area containing the device parameter information; A text recognition module, used to recognize the parameter text area through a text recognition model to obtain parameter text information of the device parameter information; A curve determination module, used to determine a parameter history curve of the target monitoring device according to the parameter text information; The warning generation module is used to generate warning information when there is abnormal jitter in the parameter history curve.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the device parameter monitoring and early warning method according to any one of claims 1 to 7 is implemented.
10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the device parameter monitoring and early warning method according to any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Time series data abnormity detection method and device
CN102945320A
Power consumer electricity consumption anomaly detection method based on machine learning
CN111695639A
Electric power communication equipment fault diagnosis method and system
CN114091699A
Image recognition method and device applied to power equipment inspection, equipment and medium
CN115482371A
Script generation method and device, electronic equipment and storage medium
CN116185408A
