Smart park equipment early warning method and system, equipment, storage medium and product

Abstract

The invention discloses a smart park device early warning method, system and device, a storage medium and a product, and relates to the technical field of smart park management, and the method comprises the steps: obtaining device monitoring data in a smart park; the equipment monitoring data are input to a preset risk prediction model, prediction processing is performed on the equipment monitoring data based on the preset risk prediction model, and a risk prediction result is obtained, and the risk prediction result is obtained through processing based on current change data of each equipment in the equipment monitoring data; and carrying out risk early warning on each device in the smart park based on the risk prediction result. According to the invention, the fault state of the equipment is accurately predicted.

Description

Technical Field

[0001] The present application relates to the field of smart park management technology, and in particular to a smart park equipment early warning method, system, equipment, storage medium and computer program product. Background Art

[0002] In the process of park construction, the traditional intelligent management of buildings has the following problems: the design, construction and application are homogeneous, which makes it difficult to meet personalized needs; the buildings and subsystems within the buildings are relatively independent, there are "information islands", and the level of intelligence is low; data collection is isolated, and system linkage is difficult to achieve; among them, since the theme requirement of the smart park is intelligent management, there will be many devices between the buildings. However, by monitoring the equipment through surveillance cameras or sensors, it is impossible to determine whether there is a fault in the equipment in real time through these monitoring data without fault analysis, and it is difficult to achieve accurate accident warning.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a smart park equipment early warning method, system, equipment, storage medium and computer program product, aiming to solve the technical problem in related technologies that equipment is monitored by monitoring cameras or sensors, but only relying on these monitoring data without fault analysis, it is impossible to determine whether there is a fault in the equipment in real time through these monitoring data, and it is difficult to achieve accurate accident early warning.

[0005] To achieve the above objectives, the present application proposes a smart park equipment early warning method, the smart park equipment early warning method comprising:

[0006] Obtain equipment monitoring data within the smart park;

[0007] The device monitoring data is input into a preset risk prediction model, and based on the preset risk prediction model, the device monitoring data is predicted and processed to obtain a risk prediction result, wherein the risk prediction result is obtained by processing the current change data of each device in the device monitoring data;

[0008] Based on the risk prediction results, risk warnings are issued for each device in the smart park.

[0009] In one embodiment, the device monitoring data includes current change data, and the step of performing prediction processing on the device monitoring data based on the preset risk prediction model to obtain a risk prediction result includes:

[0010] Dividing the current change data into a plurality of current frame data;

[0011] Calculating the change slope of each current frame data;

[0012] If the change slope does not meet the preset change standard, it is determined that the target device corresponding to the current change data fails, and a risk prediction result is output.

[0013] In one embodiment, the step of performing prediction processing on the equipment monitoring data based on the preset risk prediction model to obtain a risk prediction result further includes:

[0014] Based on the preset risk prediction model, calculating the zero-crossing period in each of the current frame data;

[0015] Based on the zero-crossing period, calculating the change time point in the current frame data;

[0016] If a delay or a phase shift occurs at the change time point, it is determined that a target device corresponding to the current change data fails, and a risk prediction result is output.

[0017] In one embodiment, the device monitoring data further includes device sound data, and the step of performing prediction processing on the device monitoring data based on the preset risk prediction model to obtain a risk prediction result includes:

[0018] Based on the preset risk prediction model, feature extraction is performed on the device sound data to obtain sound feature data;

[0019] Extracting sound spectrum features from the sound feature data;

[0020] Comparing the sound spectrum characteristics with the reference spectrum to obtain an abnormal spectrum recognition result;

[0021] Based on the abnormal spectrum recognition result and a preset fault feature library, the fault mode corresponding to the sound spectrum feature is determined, and the risk prediction result corresponding to the fault mode is output.

[0022] In one embodiment, the step of providing risk warning for each device in the smart park based on the risk prediction result includes:

[0023] The risk prediction results are visually displayed on the property management end so that the property management end can perform early warning processing on the target equipment corresponding to the risk prediction results.

[0024] In one embodiment, after the step of performing prediction processing on the equipment monitoring data based on the preset risk prediction model to obtain a risk prediction result, the step further includes:

[0025] If the error value between the risk prediction result and the actual fault result is greater than a preset error range, the device monitoring data is marked as an invalid modification sample;

[0026] If the error value between the risk prediction result and the actual fault result is less than or equal to the preset error range, the device monitoring data is marked as a valid modification sample;

[0027] Taking the invalid modified sample or the valid modified sample as newly added sample data, clustering the newly added sample data and the existing sample data to obtain clustered data;

[0028] Performing vectorization conversion on the cluster data and the old sample data to obtain a cluster sample vector and an old sample vector;

[0029] Calculating the similarity between the clustered sample vector and the old sample vector, and determining an optimized sample data set based on the similarity;

[0030] The preset risk prediction model is fine-tuned using the optimized sample data set to obtain a fine-tuned preset risk prediction model.

[0031] In addition, to achieve the above purpose, the present application also proposes a smart park equipment early warning system, the smart park equipment early warning system comprising:

[0032] A monitoring center, which is used to collect equipment monitoring data of various equipment in the smart park and send the equipment monitoring data to the park management end for processing;

[0033] A park management end, the park management end is used to obtain equipment monitoring data in the smart park; input the equipment monitoring data into a preset risk prediction model, and based on the preset risk prediction model, predict and process the equipment monitoring data to obtain a risk prediction result, wherein the risk prediction result is obtained by processing the current change data of each device in the equipment monitoring data; based on the risk prediction result, a risk warning is issued for each device in the smart park, and the risk warning result is sent to the property management end;

[0034] The property management end is used to visually display the risk warning results, and determine the target equipment for which the warning occurs based on the risk warning results, so as to perform maintenance on the target equipment.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a smart campus equipment early warning device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the smart campus equipment early warning method as described above.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the smart park equipment early warning method as described above are implemented.

[0037] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the smart park equipment early warning method as described above.

[0038] The present application proposes a smart park equipment early warning method, system, equipment, storage medium and computer program product. The present application obtains equipment monitoring data in the smart park, predicts and processes the equipment monitoring data through a preset risk prediction model, obtains risk prediction results, and then performs risk operation management on various equipment in the smart park based on the risk prediction results. Since the risk prediction results are obtained by processing the current change data of each device in the equipment monitoring data, the current change data can be processed through a preset risk prediction model, and whether the equipment has an abnormality can be determined based on the output results of the model. This can achieve timely and accurate detection and processing of equipment early warnings under real-time monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0041] Figure 1 A flowchart of the first embodiment of the smart park equipment early warning method provided in this application;

[0042] Figure 2 A flow chart of the second embodiment of the smart park equipment early warning method provided in this application;

[0043] Figure 3 This is a schematic diagram of the system architecture involved in the smart park equipment early warning method of this application;

[0044] Figure 4 This is a schematic diagram of the module structure of the smart park equipment early warning device according to an embodiment of the present application;

[0045] Figure 5 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the smart park equipment early warning method in the embodiment of the present application.

[0046] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0047] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0048] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0049] The main solutions of the embodiments of this application are:

[0050] Obtain equipment monitoring data within the smart park;

[0051] The device monitoring data is input into a preset risk prediction model, and based on the preset risk prediction model, the device monitoring data is predicted and processed to obtain a risk prediction result, wherein the risk prediction result is obtained by processing the current change data of each device in the device monitoring data;

[0052] Based on the risk prediction results, risk warnings are issued for each device in the smart park.

[0053] In the prior art, the equipment is monitored by surveillance cameras or sensors, but only relying on these monitoring data without performing fault analysis, it is impossible to determine whether the equipment has a fault in real time through these monitoring data, and it is difficult to achieve accurate accident warning.

[0054] The present application proposes a smart park equipment early warning method, system, equipment, storage medium and computer program product. The present application obtains equipment monitoring data in the smart park, predicts and processes the equipment monitoring data through a preset risk prediction model, obtains risk prediction results, and then performs risk operation management on various equipment in the smart park based on the risk prediction results. Since the risk prediction results are obtained by processing the current change data of each device in the equipment monitoring data, the current change data can be processed through the model to determine whether there is an abnormality in the equipment, so that equipment early warnings can be discovered and processed in a timely and accurate manner under real-time monitoring.

[0055] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a smart park equipment early warning device, etc. The following takes the smart park equipment early warning device as an example to illustrate this embodiment and the following embodiments.

[0056] Based on this, the embodiment of the present application provides a smart park equipment early warning method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the smart park equipment early warning method of the present application.

[0057] In this embodiment, the smart park equipment early warning method includes steps S10 to S30:

[0058] Step S10, obtaining equipment monitoring data in the smart park;

[0059] It should be noted that smart parks integrate advanced information technology and communication technology to achieve intelligent management and control of facilities, equipment, personnel and business processes within the park. There are various devices in smart parks, such as elevators, air conditioners, etc. These devices are equipped with sensors or surveillance cameras, which can be used to collect equipment monitoring data of each device.

[0060] It should be noted that the equipment monitoring data may be image data, current, voltage, pressure, vibration, equipment sound and other data generated during equipment operation, for example:

[0061] Equipment operation data: including the equipment’s switch status, operating time, load conditions, etc.

[0062] Environmental parameter data: such as temperature, humidity, and air quality within the park.

[0063] Energy consumption data: record the energy consumption of the equipment, such as electricity, water, etc.

[0064] Fault warning data: Based on the analysis of equipment operation data, the system can detect equipment anomalies and signs of failure in advance.

[0065] After the equipment monitoring data is collected, it can be processed and analyzed through models or other algorithms to determine the problems in the equipment.

[0066] Step S20, inputting the device monitoring data into a preset risk prediction model, and performing prediction processing on the device monitoring data based on the preset risk prediction model to obtain a risk prediction result, wherein the risk prediction result is obtained by processing the current change data of each device in the device monitoring data;

[0067] It should be noted that the preset risk prediction model can be a neural network model based on deep learning, a long short-term memory model, etc. Taking the neural network model based on deep learning as an example, before using the neural network model for prediction, the model has been trained. The training process is as follows:

[0068] Extract historical equipment operation sample data from the preset database;

[0069] Inputting the historical equipment operation sample data into a preset model to be trained to obtain a predicted equipment failure state;

[0070] Calculate the difference between the predicted equipment failure state and the equipment failure state label corresponding to the historical equipment operation sample data to obtain an error result;

[0071] Determining whether the error result meets the error standard indicated by a preset error threshold range;

[0072] If the error result does not meet the error standard indicated by the preset error threshold range, return to the step of inputting the historical operation sample data into the preset model to be trained to obtain the step of predicting the equipment failure state, and stop training until the error result meets the error standard indicated by the preset error threshold range to obtain a preset risk prediction model that meets the accuracy conditions.

[0073] It should be noted that the method of predicting and processing the equipment monitoring data through the preset risk prediction model can be: extracting features from the equipment monitoring data to obtain feature data, processing the feature data through a convolutional network, and finally outputting the equipment failure probability corresponding to the equipment monitoring data from the fully connected layer to obtain the risk prediction result, and then, determining whether each device has a fault based on the risk prediction result to determine whether it needs to be repaired or maintained.

[0074] It should be noted that in the process of extracting features from the equipment monitoring data by the preset risk prediction model, the current change features of the equipment monitoring data are extracted. The equipment will have current changes over a period of time, and for normal equipment, the current changes are basically stable and will not fluctuate too much. In related technologies, most of them determine whether the equipment is faulty by judging whether the equipment current is greater than a current threshold. However, for some aging or poorly contacted equipment, an occasional increase or decrease in current is normal, but it can be easily misjudged as an equipment failure, thereby triggering an erroneous equipment warning, increasing the workload of property personnel. In this embodiment, when the current change of the equipment is large, it can be determined that the currently detected equipment has a fault or other problem, and a warning needs to be reported.

[0075] It should be noted that equipment monitoring data can also be equipment image data. Use cameras or drones and other equipment to regularly collect equipment image data. Ensure that the image quality is high and the resolution is sufficient to clearly display the various parts of the equipment. Annotate the collected images and mark the images in normal and faulty states. You can use manual annotation or semi-automatic annotation tools. Use the model to predict risks in real time, collect equipment images regularly, conduct risk assessments through the model, generate reports, guide maintenance work, use visualization tools to explain the model's prediction results, generate detailed prediction reports, including the equipment's status, potential risks, recommended maintenance measures, etc., collect user feedback on the model's prediction results, and understand the actual application effect of the model. Based on feedback and new data, continuously optimize the model to improve the accuracy and reliability of the prediction.

[0076] It should be noted that the risk prediction result may be the probability of equipment failure. When the probability of equipment failure is greater than a preset threshold (eg, 70%, 80%, etc.), it can be determined that the equipment fails.

[0077] In a feasible implementation manner, the device monitoring data includes current change data, and the step S20 of performing prediction processing on the device monitoring data based on the preset risk prediction model to obtain a risk prediction result includes:

[0078] Dividing the current change data into a plurality of current frame data;

[0079] It should be noted that current frame data refers to current data collected within a certain time window. Current values ​​are usually recorded at fixed time intervals (such as milliseconds or microseconds) to form a data frame. The current change data collected within a certain time period is split into multiple current frame data.

[0080] Calculating the change slope of each current frame data;

[0081] It should be noted that the change slope of the current frame data can be the degree of change of the current value within a preset time period (e.g., 10S, 1h, etc.). The slope of each time point is calculated using a point-by-point calculation or a moving window calculation method, and the slope data is stored for subsequent analysis. The analysis of the current change slope can be used to represent:

[0082] Instantaneous change: A large absolute value of the slope indicates that the current has changed dramatically in a short period of time, which may be a sign of equipment startup, stop, or failure.

[0083] Trend change: The sign and size of the slope can reflect the changing trend of the current, such as a gradual increase or decrease.

[0084] Abnormal detection: By setting a threshold, when the slope exceeds the threshold, an alarm is triggered to indicate a possible fault.

[0085] If the change slope does not meet the preset change standard, it is determined that the target device corresponding to the current change data fails, and a risk prediction result is output.

[0086] It should be noted that the preset change standard can be a slope threshold of the change slope. When the change slope exceeds the normal change threshold range, it is determined that the target device corresponding to the current change data has a fault, and the failure probability corresponding to the device is output as a risk prediction result.

[0087] In a feasible implementation manner, the step S20 of performing prediction processing on the equipment monitoring data based on the preset risk prediction model to obtain a risk prediction result further includes:

[0088] Based on the preset risk prediction model, calculating the zero-crossing period in each of the current frame data;

[0089] It should be noted that the zero-crossing point refers to the point where the current value changes from positive to negative or from negative to positive, and the zero-crossing period refers to the time interval when the current transitions from the positive half cycle to the negative half cycle or from the negative half cycle to the positive half cycle. It can help identify the frequency, periodic changes and potential faults of the current, analyze the fluctuations of the zero-crossing period, and determine whether the periodic changes of the current are stable. Abnormal changes in the zero-crossing period may indicate equipment faults, such as harmonic interference, short circuit, overload, etc.

[0090] Based on the zero-crossing period, calculating the change time point in the current frame data;

[0091] It should be noted that the change time point usually refers to the time point when the current waveform changes significantly, such as the zero crossing point, peak point, valley point, etc. When the change time point changes, the waveform data of the overall current frame data will be offset, then it can be determined that the current has undergone large fluctuations, and it can be determined that the equipment is faulty.

[0092] If a delay or a phase shift occurs at the change time point, it is determined that a target device corresponding to the current change data fails, and a risk prediction result is output.

[0093] It should be noted that when the waveform of the current frame data fluctuates greatly, there will be a large delay at the change time point. When the delay of the waveform data exceeds the preset delay threshold, it is determined that the target device corresponding to the flow change data has a fault. The preset delay threshold can be 1ms, 5ms, etc., and there is no specific limitation.

[0094] Step S30: Based on the risk prediction results, risk warning is issued for each device in the smart park.

[0095] It should be noted that based on the risk prediction results, the faulty equipment can be located and risk warnings can be issued for each device in the smart park, thereby improving the operational efficiency and safety of the park.

[0096] In a feasible implementation manner, the step S30 of providing risk warning for each device in the smart park based on the risk prediction result includes:

[0097] The risk prediction results are visually displayed on the property management end so that the property management end can perform early warning processing on the target equipment corresponding to the risk prediction results.

[0098] It should be noted that visually displaying the risk prediction results on the property management side can help property management personnel to more intuitively understand the operating status and potential risks of the equipment, so as to take early warning measures in a timely manner. After the property management side receives the risk prediction results, for example, the risk prediction results show which equipment has failed and the location of the fault point, so that risk warnings can be issued for the target equipment with the fault.

[0099] It should be noted that after obtaining the risk prediction results, the equipment failures can be graded according to the different failure probabilities of the risk warning results. For example, the processing level of a high failure probability will be increased accordingly. The grading method can also be based on the importance of the equipment. The classification can be divided into level one, level two, level three, etc. When the equipment affects the normal operation of the park, it needs to be processed first. For example, elevators, servers and other equipment need to be processed as soon as the equipment fails.

[0100] In a feasible implementation manner, after the step S30 of performing prediction processing on the equipment monitoring data based on the preset risk prediction model to obtain the risk prediction result, the step further includes:

[0101] If the error value between the risk prediction result and the actual fault result is greater than a preset error range, the device monitoring data is marked as an invalid modification sample;

[0102] It should be noted that when the error value between the risk prediction result and the actual fault result is greater than the preset error range, and the accuracy of the risk prediction result does not meet the model accuracy required by the user, it means that the current equipment monitoring data is invalid or biased, and is marked as an invalid modified sample.

[0103] If the error value between the risk prediction result and the actual fault result is less than or equal to the preset error range, the device monitoring data is marked as a valid modification sample;

[0104] It should be noted that when the error value between the risk prediction result and the actual fault result is less than or equal to the preset error range, and the accuracy of the risk prediction result reaches the model accuracy required by the user, it means that the current equipment monitoring data is valid, and the equipment monitoring data is marked as a valid modification sample.

[0105] Taking the invalid modified sample or the valid modified sample as newly added sample data, clustering the newly added sample data and the existing sample data to obtain clustered data;

[0106] It should be noted that the invalid modified samples or the valid modified samples are used as sample data, and the sample data is used as the input of the model. At the same time, the newly added sample data and the existing sample data are clustered. After the clustering data is determined, the clustering data is used to fine-tune the preset configuration model to obtain a fine-tuned clustering model.

[0107] Performing vectorization conversion on the cluster data and the old sample data to obtain a cluster sample vector and an old sample vector;

[0108] It should be noted that after the cluster data and the old sample data are vectorized by doc2vec (an algorithm for converting document samples into a fixed-length vector), the cluster sample vector and the old sample vector are obtained. The purpose of the vectorization conversion is to calculate the cosine distance between each vector, thereby calculating the similarity of the two data.

[0109] Calculating the similarity between the clustered sample vector and the old sample vector, and determining an optimized sample data set based on the similarity;

[0110] It should be noted that the method for determining the optimized sample data set is: traverse the category to which each newly added sample belongs, delete the sample with the closest cosine distance to the invalid sample, and directly add the valid sample to the fine-tuning data set to increase the proportion of high-quality samples and reduce the proportion of harmful samples.

[0111] The preset risk prediction model is fine-tuned using the optimized sample data set to obtain a fine-tuned preset risk prediction model.

[0112] It should be noted that incremental SFT (Supervised Fine-Tuning, using labeled sample data to train and adjust model parameters, and backing up and synchronizing the changed sample set) is performed on the optimized sample data set to fine-tune the existing preset risk prediction model weights so that it can generate more accurate prediction results later.

[0113] The present application proposes a smart park equipment early warning method, system, equipment, storage medium and computer program product. The present application obtains equipment monitoring data in the smart park, predicts and processes the equipment monitoring data through a preset risk prediction model, obtains risk prediction results, and then performs risk operation management on various equipment in the smart park based on the risk prediction results. Since the risk prediction results are obtained by processing the current change data of each device in the equipment monitoring data, the current change data can be processed through a preset risk prediction model, and whether the equipment has an abnormality can be determined based on the output results of the model. This can achieve timely and accurate detection and processing of equipment early warnings under real-time monitoring.

[0114] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , the equipment monitoring data also includes equipment sound data, and the step S20 of performing prediction processing on the equipment monitoring data based on the preset risk prediction model to obtain a risk prediction result also includes:

[0115] Step S21, based on the preset risk prediction model, feature extraction is performed on the device sound data to obtain sound feature data;

[0116] It should be noted that the equipment sound data is the sound signal of the equipment during normal and abnormal operation. The sound signal can be collected from the motor, bearing, gearbox and other components to ensure sufficient sample data. After collecting the sound features, the collected sound signal is filtered to remove noise and interference signals and retain useful spectrum information.

[0117] Step S22, extracting sound spectrum features from the sound feature data;

[0118] It should be noted that feature extraction can be to extract the time domain features or frequency domain features of the device sound data, and the process of extracting the sound spectrum features can be:

[0119] Fourier transform (FFT): Convert the time domain signal into the frequency domain signal to obtain the spectrum of the sound.

[0120] Peak frequency: Extract the peak frequency in the spectrum graph, which reflects the main frequency component of the signal.

[0121] Frequency band energy: Calculates the energy of different frequency bands to reflect the energy distribution of the signal in different frequency ranges.

[0122] Harmonic component: Extract the harmonic component in the spectrum to reflect the periodic characteristics of the signal.

[0123] Total Harmonic Distortion (THD): Calculates the total harmonic distortion of a signal to assess the purity of the signal.

[0124] Step S23, comparing the sound spectrum characteristics with the reference spectrum to obtain an abnormal spectrum recognition result;

[0125] It should be noted that the reference spectrum is the sound spectrum of the device in normal operation. By comparing the sound spectrum characteristics with the reference spectrum, it can be determined whether the sound spectrum of the device is normal, thereby determining whether the device has a fault.

[0126] It should be noted that the process of comparing the sound spectrum characteristics with the reference spectrum can be:

[0127] Euclidean distance: Calculates the Euclidean distance between the reference spectrum and the test spectrum to reflect the similarity between the two. When the Euclidean distance between the test spectrum and the reference spectrum exceeds the set threshold, it is identified as an abnormal spectrum.

[0128] Cosine similarity: Calculates the cosine similarity between the reference spectrum and the test spectrum to reflect the directional similarity between the two. When the cosine similarity between the test spectrum and the reference spectrum is lower than the set threshold, it is identified as an abnormal spectrum.

[0129] Band energy ratio: Calculates the energy ratio of the reference spectrum and the test spectrum in different frequency bands to reflect the difference in energy distribution. When the energy of the test spectrum in certain frequency bands is significantly different from that of the reference spectrum, it is identified as an abnormal spectrum.

[0130] Step S24, based on the abnormal spectrum recognition result and a preset fault feature library, determining the fault mode corresponding to the sound spectrum feature, and outputting the risk prediction result corresponding to the fault mode.

[0131] It should be noted that the preset fault feature library is constructed by collecting sound spectrum features under various fault modes. The preset fault feature library can match the abnormal spectrum features with the features in the fault feature library to determine the most similar fault mode, where the fault mode can be a bearing fault, a controller fault, etc. According to the fault mode, it is determined how the equipment should handle the fault.

[0132] It should be noted that after the failure mode is determined, the risk prediction result corresponding to the failure mode is output.

[0133] In this embodiment, by using the equipment sound data to judge the faults of various equipment models in the smart park, the failure mode of each equipment can be determined, thereby achieving accurate positioning of the fault.

[0134] The present application also provides a smart park equipment early warning system, the smart park equipment early warning system comprising:

[0135] A monitoring center, which is used to collect equipment monitoring data of various equipment in the smart park and send the equipment monitoring data to the park management end for processing;

[0136] A park management end, the park management end is used to obtain equipment monitoring data in the smart park; input the equipment monitoring data into a preset risk prediction model, and based on the preset risk prediction model, predict and process the equipment monitoring data to obtain a risk prediction result, wherein the risk prediction result is obtained by processing the current change data of each device in the equipment monitoring data; based on the risk prediction result, a risk warning is issued for each device in the smart park, and the risk warning result is sent to the property management end;

[0137] The property management end is used to visually display the risk warning results, and determine the target equipment for which the warning occurs based on the risk warning results, so as to perform maintenance on the target equipment.

[0138] For example, in order to help understand the implementation process of the smart park equipment early warning method obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 3 , Figure 3 A system architecture diagram of a smart park equipment early warning method is provided, specifically:

[0139] The monitoring data of each device in the smart park is obtained through various monitoring devices (such as cameras) in the monitoring center, and the device monitoring data is sent to the park management end, where the park management end is used to analyze and process the received device monitoring data, output risk prediction results, and then send the risk prediction results to the property management end so that the property personnel can perform maintenance on the faulty equipment.

[0140] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the smart park equipment early warning method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0141] This application also provides a smart park equipment early warning device, please refer to Figure 4 , the smart park equipment early warning device includes:

[0142] The acquisition module 10 is used to obtain the equipment monitoring data in the smart park;

[0143] The processing module 20 is used to input the device monitoring data into a preset risk prediction model, and perform prediction processing on the device monitoring data based on the preset risk prediction model to obtain a risk prediction result, wherein the risk prediction result is obtained by processing the current change data of each device in the device monitoring data;

[0144] The early warning module 30 is used to issue risk early warning to each device in the smart park based on the risk prediction result.

[0145] Optionally, the processing module includes:

[0146] A dividing unit, used for dividing the current change data into a plurality of current frame data;

[0147] A calculation unit, used for calculating the change slope of each current frame data;

[0148] The first output unit is used to determine that a target device corresponding to the current change data fails if the change slope does not meet a preset change standard, and output a risk prediction result.

[0149] Optionally, the processing module further includes:

[0150] A first calculation unit, configured to calculate a zero-crossing period in each of the current frame data based on the preset risk prediction model;

[0151] A second calculation unit, configured to calculate a change time point in the current frame data based on the zero-crossing period;

[0152] The second output unit is used to determine that a target device corresponding to the current change data has a fault if a delay or a phase shift occurs at the change time point, and output a risk prediction result.

[0153] Optionally, the processing module further includes:

[0154] A feature extraction unit, configured to extract features from the device sound data based on the preset risk prediction model to obtain sound feature data;

[0155] An extraction unit, used for extracting sound spectrum features from the sound feature data;

[0156] A comparison unit, used to compare the sound spectrum feature with a reference spectrum to obtain an abnormal spectrum recognition result;

[0157] A determination unit is used to determine the fault mode corresponding to the sound spectrum feature based on the abnormal spectrum recognition result and a preset fault feature library, and output a risk prediction result corresponding to the fault mode.

[0158] Optionally, the early warning module includes:

[0159] The visualization display unit is used to visualize the risk prediction results on the property management end so that the property management end can perform early warning processing on the target equipment corresponding to the risk prediction results.

[0160] Optionally, the device further comprises:

[0161] A first marking module, configured to mark the device monitoring data as an invalid modification sample if the error value between the risk prediction result and the actual fault result is greater than a preset error range;

[0162] A second marking module, used for marking the equipment monitoring data as a valid modification sample if the error value between the risk prediction result and the actual fault result is less than or equal to a preset error range;

[0163] A clustering module, configured to use the invalid modified sample or the valid modified sample as newly added sample data, and cluster the newly added sample data with the existing sample data to obtain clustered data;

[0164] A vectorization conversion module, used for performing vectorization conversion on the cluster data and the old sample data to obtain a cluster sample vector and an old sample vector;

[0165] A calculation module, used for calculating the similarity between the clustered sample vector and the old sample vector, and determining an optimized sample data set based on the similarity;

[0166] The fine-tuning module is used to fine-tune the preset risk prediction model through the optimized sample data set to obtain a fine-tuned preset risk prediction model.

[0167] The smart park equipment early warning device provided by this application adopts the smart park equipment early warning method in the above embodiment, which can solve the technical problem of smart park equipment early warning. Compared with the prior art, the beneficial effects of the smart park equipment early warning device provided by this application are the same as the beneficial effects of the smart park equipment early warning method provided by the above embodiment, and the other technical features in the smart park equipment early warning device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0168] The present application provides a smart campus equipment early warning device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the smart campus equipment early warning method in the above-mentioned embodiment one.

[0169] Reference below Figure 5, which shows a schematic diagram of the structure of a smart park equipment warning device suitable for implementing the embodiment of the present application. The smart park equipment warning device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The smart park equipment warning device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0170] like Figure 5 As shown, the smart park equipment early warning device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the smart park equipment early warning device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the smart park equipment early warning device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a smart park equipment early warning device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0171] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0172] The smart park equipment early warning device provided by this application adopts the smart park equipment early warning method in the above embodiment, which can solve the technical problem of smart park equipment early warning. Compared with the prior art, the beneficial effects of the smart park equipment early warning device provided by this application are the same as the beneficial effects of the smart park equipment early warning method provided by the above embodiment, and the other technical features in the smart park equipment early warning device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0173] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0174] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0175] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the smart park equipment early warning method in the above-mentioned embodiment.

[0176] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0177] The above-mentioned computer-readable storage medium may be included in the smart park equipment early warning device; or it may exist independently without being assembled into the smart park equipment early warning device.

[0178] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the smart park equipment early warning device, the smart park equipment early warning device:

[0179] Obtain equipment monitoring data within the smart park;

[0180] The device monitoring data is input into a preset risk prediction model, and based on the preset risk prediction model, the device monitoring data is predicted and processed to obtain a risk prediction result, wherein the risk prediction result is obtained by processing the current change data of each device in the device monitoring data;

[0181] Based on the risk prediction results, risk warnings are issued for each device in the smart park. Computer program codes for performing the operations of the present application can be written in one or more programming languages ​​or a combination thereof, and the above-mentioned programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0182] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0183] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0184] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned smart park equipment early warning method, and can solve the technical problem of smart park equipment early warning. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the smart park equipment early warning method provided in the above-mentioned embodiment, and will not be repeated here.

[0185] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned smart park equipment early warning method.

[0186] The computer program product provided by this application can solve the technical problem of early warning of smart park equipment. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the early warning method of smart park equipment provided by the above embodiment, which will not be repeated here.

[0187] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A smart park equipment early warning method, characterized in that: Applied to the park management end, the method includes: Obtain equipment monitoring data within the smart park; The device monitoring data is input into a preset risk prediction model, and based on the preset risk prediction model, the device monitoring data is predicted and processed to obtain a risk prediction result, wherein the risk prediction result is obtained by processing the current change data of each device in the device monitoring data; Based on the risk prediction results, risk warnings are issued for each device in the smart park.

2. The method according to claim 1, characterized in that The device monitoring data includes current change data, and the step of performing prediction processing on the device monitoring data based on the preset risk prediction model to obtain a risk prediction result includes: Dividing the current change data into a plurality of current frame data; Calculating the change slope of each current frame data; If the change slope does not meet the preset change standard, it is determined that the target device corresponding to the current change data fails, and a risk prediction result is output.

3. The method according to claim 2, characterized in that The step of performing prediction processing on the equipment monitoring data based on the preset risk prediction model to obtain a risk prediction result also includes: Based on the preset risk prediction model, calculating the zero-crossing period in each of the current frame data; Based on the zero-crossing period, calculating the change time point in the current frame data; If a delay or a phase shift occurs at the change time point, it is determined that a target device corresponding to the current change data fails, and a risk prediction result is output.

4. The method according to claim 1, characterized in that The device monitoring data also includes device sound data. The step of performing prediction processing on the device monitoring data based on the preset risk prediction model to obtain a risk prediction result includes: Based on the preset risk prediction model, feature extraction is performed on the device sound data to obtain sound feature data; Extracting sound spectrum features from the sound feature data; Comparing the sound spectrum characteristics with the reference spectrum to obtain an abnormal spectrum recognition result; Based on the abnormal spectrum recognition result and a preset fault feature library, the fault mode corresponding to the sound spectrum feature is determined, and the risk prediction result corresponding to the fault mode is output.

5. The method according to claim 1, characterized in that The step of providing risk warning for each device in the smart park based on the risk prediction result includes: The risk prediction results are visually displayed on the property management end so that the property management end can perform early warning processing on the target equipment corresponding to the risk prediction results.

6. The method according to claim 1, characterized in that After the step of performing prediction processing on the equipment monitoring data based on the preset risk prediction model to obtain a risk prediction result, the method further includes: If the error value between the risk prediction result and the actual fault result is greater than a preset error range, the device monitoring data is marked as an invalid modification sample; If the error value between the risk prediction result and the actual fault result is less than or equal to the preset error range, the device monitoring data is marked as a valid modification sample; Taking the invalid modified sample or the valid modified sample as newly added sample data, clustering the newly added sample data and the existing sample data to obtain clustered data; Performing vectorization conversion on the cluster data and the old sample data to obtain a cluster sample vector and an old sample vector; Calculating the similarity between the clustered sample vector and the old sample vector, and determining an optimized sample data set based on the similarity; The preset risk prediction model is fine-tuned using the optimized sample data set to obtain a fine-tuned preset risk prediction model.

7. A smart park equipment early warning system, characterized in that: The smart park equipment early warning system includes: A monitoring center, which is used to collect equipment monitoring data of various devices in the smart park and send the equipment monitoring data to the park management end for processing; A park management end, the park management end is used to obtain equipment monitoring data in the smart park; input the equipment monitoring data into a preset risk prediction model, and based on the preset risk prediction model, predict and process the equipment monitoring data to obtain a risk prediction result, wherein the risk prediction result is obtained by processing the current change data of each device in the equipment monitoring data; based on the risk prediction result, a risk warning is issued for each device in the smart park, and the risk warning result is sent to the property management end; The property management end is used to visually display the risk warning results, and determine the target equipment for which the warning occurs based on the risk warning results, so as to perform maintenance on the target equipment.

8. A smart park equipment early warning device, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the smart park equipment early warning method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the smart park equipment early warning method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the smart park equipment early warning method as described in any one of claims 1 to 6 are implemented.

Images