Electric energy meter communication module state detection method and system based on data analysis

Abstract

The invention relates to the field of data processing, and relates to an electric energy meter communication module state detection method and system based on data analysis, and the method comprises the steps: collecting historical data packets of electric energy meter communication modules of various lengths, and environment data of historical moments corresponding to the historical data packets; a plurality of historical data packets with each length are provided; for the historical data packet of each length, obtaining the interference degree of each communication data to the environment when the state of the communication module is judged, and the importance degree of each communication data to the judgment of the state of the communication module; and constructing a corresponding classification model, training the classification model to obtain a state detection model, collecting communication data packets sent by the electric energy meter communication module in real time, and obtaining the state of the electric energy meter communication module in combination with the state detection model corresponding to the historical data packet with the closest length. By adopting the method, the accuracy of state detection of the communication module can be greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and more specifically, to a method and system for detecting the state of an electric energy meter communication module based on data analysis. Background Art

[0002] With the rapid development of the economy, the demand for electricity in all walks of life is increasing, and the role of electric energy meters is becoming more and more important. Electric energy meters are instruments used to measure electrical energy, also known as watt-hour meters, fire meters and kilowatt-hour meters, which refer to instruments that measure various electrical quantities. When using electric energy meters, please note: In the case of low voltage (below 500 volts) and small current (tens of amperes), the electric energy meter can be directly connected to the circuit for measurement. In the case of high voltage or high current, the electric energy meter cannot be directly connected to the line and needs to be used in conjunction with a voltage transformer or a current transformer.

[0003] The electric energy meter usually includes a power module, a metering module, a display module, a communication module, a safety module, a clock module, a storage module and a power on / off module. The communication module is used for data transmission and communication with a host or other devices.

[0004] After collecting the power consumption data of the power grid, the energy meter will transmit it to the monitoring center or power supply company through its communication module. If the communication module of the energy meter fails, the collected data cannot be transmitted in time. Therefore, it is very important to detect the fault of the energy meter communication module. The existing detection method mainly relies on simple signal transmission status (such as whether the connection is successful, whether the data is sent successfully, etc.) to detect the status of the energy meter communication module. Since this method does not take into account the interference of environmental factors on the status detection of the energy meter communication module, it may cause misjudgment when detecting the status of the energy meter communication module, resulting in poor accuracy of the status detection result. Summary of the invention

[0005] In order to solve the technical problem that the detection result accuracy of the electric energy meter communication module detection method in the prior art is poor, the present invention provides solutions in the following aspects.

[0006] In a first aspect, the present invention provides a method for detecting the state of an electric energy meter communication module based on data analysis, comprising: collecting historical data packets of the electric energy meter communication module of various lengths, and environmental data corresponding to historical moments of each historical data packet; there are multiple historical data packets of each length; For each length of historical data packets, obtain the degree of interference from the environment when judging the state of the communication module for each communication data, as well as the importance of various communication data for judging the state of the communication module; build a classification model, train it using the loss function to obtain a state detection model, and the loss function calculation expression used when training the classification model corresponding to the i-th length data packet is:

[0007] In the formula, For the The classification loss function of the nth communication data in the classification model corresponding to the data packet of this length; For the The label of the communication module status corresponding to the secondary communication data; is the output of the classification model Prediction of communication data The probability of For the The mth type of communication data corresponding to the data packet of the type length judges the interference degree of the environment when the state of the communication module is judged; For the The length of the data packet corresponding to The importance of the communication data for determining the status of the communication module; The communication data packets sent by the electric energy meter communication module are collected in real time, and the state of the electric energy meter communication module is obtained by combining the state detection model corresponding to the historical data packet with the closest length to it; assuming that there are two types of historical data packet lengths closest to the length of the communication data packet collected in real time, the state detection model corresponding to the historical data packet with a smaller length than the communication data packet collected in real time is selected to detect the electric energy meter communication module.

[0008] The beneficial effect is that when constructing a classification model, the method for detecting the state of the electric energy meter communication module of the present invention takes into account that when using data packets to detect the communication module, data packets of different lengths are subject to different degrees of environmental interference, and constructs different classification models (i.e., clustering modeling) for historical data packets of different lengths. After collecting real-time communication data packets, the classification model of the historical data packet with the closest length is selected to detect the communication module, thereby greatly improving the accuracy of communication module state detection.

[0009] In addition, in the process of training the classification model, the different types of communication data may have different importance in judging the status of the communication module, and the interference of environmental data on the communication data in judging the status of the communication module is also taken into account. By correcting the loss function based on the degree of interference of environmental data and the importance of various communication data in judging the status of the communication module, the limitations of a single data source are avoided. The classification model can also suppress real-time environmental interference (such as sudden temperature changes) and improve the classification accuracy of the model in complex environments.

[0010] Preferably, The method for calculating the degree of interference of the environment when judging the state of the communication module by the mth type of communication data corresponding to the data packet of the type length comprises: calculating the mth type of communication data corresponding to the data packet of the type length The mth type of communication data corresponding to the data packet of the type length is used to judge the interference degree of the communication module state caused by temperature, humidity and voltage fluctuation; The interference degree due to temperature, the interference degree due to humidity and the interference degree due to voltage fluctuation are weighted and summed to obtain the first The mth type of communication data corresponding to the data packet of the type length is used to judge the interference degree of the environment when the state of the communication module is judged.

[0011] The beneficial effect is that when calculating the degree of interference of environmental data on communication data in judging the state of the electric energy meter communication module, the degree of interference of temperature, humidity and voltage fluctuations on judging the state of the electric energy meter communication module is comprehensively considered, thereby making the calculation result of the degree of interference of environmental data on communication data in judging the state of the electric energy meter communication module more accurate.

[0012] Preferably, The calculation expression for the degree of interference from the environment when the mth type of communication data corresponding to the data packet of the type length is used to judge the state of the communication module is: ; In the formula, For the The information carrying capacity of the environmental data sequence; Respectively The information carrying capacity of temperature sequence, humidity sequence and voltage fluctuation sequence under the data packets of different lengths, , and Respectively represent The mth type of communication data corresponding to the data packet of the type length is used to judge the interference degree of the communication module state caused by temperature, humidity and voltage fluctuation.

[0013] Its beneficial effect is as follows: when calculating the degree of interference of environmental data on communication data for determining the state of the communication module of the electric energy meter, the present invention further takes into account the relationship between the information carrying capacity of the environmental data and the degree of interference on the state of the communication module. When performing weighted summation on the interference degrees corresponding to various environmental data, a larger weight is given to environmental data with a larger information carrying capacity, and a smaller weight is given to environmental data with a smaller information carrying capacity, thereby further improving the accuracy of the degree of interference of environmental data on communication data for determining the state of the communication module of the electric energy meter.

[0014] Preferably, The information carrying capacity of environmental data The calculation expression is: ; In the formula, For the The length of the data packet corresponding to The standard deviation of the environmental data series, For the The length of the data packet corresponding to Environmental data series and Pearson correlation coefficient of environmental data series, They represent temperature series, humidity series and voltage fluctuation series respectively.

[0015] Preferably, The calculation expression for the degree of interference of temperature when judging the state of the communication module by the mth type of communication data corresponding to the data packet of the type length is: ; In the formula, and Respectively The maximum and minimum values ​​in the mth communication data sequence corresponding to the data packet of the length, and Respectively The maximum and minimum values ​​of the temperature in the temperature sequence under the data packet of the same length. is the hyperbolic tangent function, For the The absolute value of the Pearson correlation coefficient between the temperature sequence under the data packet of the mth length and the mth communication data sequence.

[0016] Preferably, The length of the data packet corresponding to The importance of the mth communication data and the information gain of the mth communication data corresponding to the i-th length data packet for judging the state of the electric energy meter communication module is positively correlated, and the calculation expression of the information gain is: ; In the formula, is the information entropy of the state 𝑦 of the electric energy meter communication module under the 𝑖th length data packet; It is the conditional entropy of the state y of the electric energy meter communication module after the mth communication data is known under the i-th length data packet.

[0017] Preferably, the communication data includes communication time, signal strength and packet loss rate.

[0018] Preferably, the method further comprises: performing linear interpolation processing on the collected historical data packets and environmental data, and performing denoising on them by adopting wavelet transform.

[0019] Preferably, the classification model is a neural network model or a machine learning model.

[0020] In a second aspect, the present invention also provides an electric energy meter communication module status detection system based on data analysis, comprising a processor and a memory, wherein the memory stores computer program instructions for detecting the status of the electric energy meter communication module, and when the computer program instructions are executed by the processor, the electric energy meter communication module status detection method based on data analysis of the present invention is implemented.

[0021] In summary, the beneficial effect of the present invention is that the method of the present invention can greatly improve the accuracy of the state detection result of the communication module of the electric energy meter. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a flow chart schematically showing a method for detecting the state of an electric energy meter communication module based on data analysis according to an embodiment of the present invention; Figure 2 The figure schematically shows the structure of a power meter communication module status detection system based on data analysis according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0024] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0025] Embodiment of the method for detecting the state of the electric energy meter communication module based on data analysis: like Figure 1 As shown, the method for detecting the state of an electric energy meter communication module based on data analysis of the present invention comprises: S101, collecting various lengths of historical data packets of the communication module of the electric energy meter and corresponding environmental data, specifically: collecting various lengths of historical data packets of the communication module of the electric energy meter, and environmental data corresponding to each historical data packet at a historical moment; there are multiple historical data packets of each length; After collecting the historical data packet, it is necessary to obtain the state of the electric energy meter communication module corresponding to the historical data packet so as to label the historical data packet. The state of the communication module includes two states: normal and abnormal. The label of the normal state is 0, and the label of the abnormal state is 1. Indicates that the energy meter communication module status is normal. Indicates that the energy meter communication module status is abnormal.

[0026] The environmental data corresponding to the historical moment of the historical data packet refers to the environmental data collected at the historical moment corresponding to the historical data packet. When collecting the historical data packets, the state tags of the electric energy meter communication modules corresponding to each historical data packet are collected.

[0027] The historical data packets of the communication module of the electric energy meter can be collected through the sensor network and the communication interface device.

[0028] S102, obtaining the interference degree of the environmental data on the communication module state judgment and the importance of the communication data on the communication module state judgment, specifically: for each length of historical data packets, obtaining the interference degree of each communication data when judging the communication module state by the environment, and the importance of various communication data for judging the communication module state; In this embodiment, judging the state of the communication module by a certain type of communication data means judging the state of the communication module according to the type of communication data.

[0029] For the communication data and environmental data of historical data packets with the same length, the degree of interference of environmental data on communication data in judging the status of the electric energy meter communication module and the importance of communication data in judging the status of the electric energy meter communication module are calculated, which provides a basis for subsequent scenario modeling and avoids the insufficient adaptability of the global model to different data packet lengths.

[0030] S103, obtaining the state detection model corresponding to the historical data packets of various lengths, specifically: for each length of the historical data packets, respectively construct a classification model, train it using the loss function to obtain the state detection model, and the loss function calculation expression used when training the classification model corresponding to the data packet of the i-th length is:

[0031] In the formula, For the The classification loss function of the nth communication data in the classification model corresponding to the data packet of this length; For the The label of the communication module status corresponding to the secondary communication data; is the output of the classification model Prediction of communication data The probability of For the The mth type of communication data corresponding to the data packet of the type length judges the interference degree of the environment when the state of the communication module is judged; For the The length of the data packet corresponding to The importance of the communication data for determining the status of the communication module.

[0032] In the When the label of the communication module status corresponding to the communication data is 1 (i.e. the communication module is abnormal), , The bigger, The smaller it is, the more difficult it is to classify the communication data, the larger the penalty factor of the loss function for judging the communication data, and the larger the corresponding loss function value; conversely, , The smaller, The larger it is, the less difficult it is to classify the communication data, the smaller the penalty factor of the loss function for judging the communication data, and the smaller the corresponding loss function value.

[0033] Similarly, in When the label of the communication module status corresponding to the communication data is 0 (i.e. the communication module is normal), , The bigger, The larger it is, that is, when the communication data is judged incorrectly, the larger the penalty factor of the loss function is, and the larger the corresponding loss function value is; conversely, , The smaller, The smaller it is, that is, the smaller the penalty factor of the loss function is when the communication data is judged incorrectly, and the smaller the corresponding loss function value is.

[0034] Therefore, when the loss function calculation expression of the loss function of this embodiment is used to calculate the loss function, it can be ensured that a smaller loss function value is set when the communication data is more difficult to classify, and a larger loss function value is set when the communication data is less difficult to classify, thereby making the training effect of the classification model better.

[0035] In this embodiment, when calculating the loss function, the interference degree of the environmental data under the i-th length data packet on the communication data to judge the state of the electric energy meter communication module and the importance of the communication data for judging the state of the electric energy meter communication module are introduced to modify the classification model loss function. Compared with relying only on the original two-classification cross entropy loss function, the loss function can more accurately and effectively judge whether the state of the electric energy meter communication module is abnormal during the training process. The method for calculating the loss function in this embodiment can more accurately distinguish the credibility of each communication data under different length data packets, provide more refined discrimination information, thereby improving the model's ability to distinguish different states (normal and abnormal) of the electric energy meter communication module, and ultimately make the loss function more discriminating, and can better optimize the classification performance during training, especially when the electric energy meter communication module is greatly interfered by environmental characteristics.

[0036] In this embodiment, the communication data includes communication time, signal strength and packet loss rate. In other embodiments, the communication data may also include other types of data.

[0037] In this embodiment, the classification model is a neural network model or a machine learning model. In other embodiments, the classification model may also be other suitable classification models.

[0038] If the classification model is a neural network model, the classification model training process corresponding to the i-th length historical data packet is as follows: A. Obtain the working status of the electric energy meter communication module corresponding to each i-th length historical data packet collected, and then label each i-th length historical data packet to obtain a training set; For a certain historical data packet, if the working state of the corresponding electric energy meter communication module is normal, the label of the historical data packet is 0; otherwise, the label of the historical data packet is 1.

[0039] B. Select the network architecture of the classification model and initialize the parameters; You can choose convolutional neural network (CNN) or recurrent neural network (RNN).

[0040] The initialization parameters include initializing the weights and biases in the network, and the initialization method can adopt a random initialization method.

[0041] C. Forward propagation: The input data is calculated through the network to obtain the predicted output.

[0042] D. Calculate loss: Calculate the value of the loss function based on the predicted output and the true label.

[0043] E. Back propagation: Calculate the gradient through the chain rule and update the network parameters to reduce the loss.

[0044] F. Parameter update: Use the optimizer to update the network parameters according to the calculated gradients.

[0045] G. Set hyperparameters: Determine hyperparameters such as learning rate, batch size, and number of training rounds.

[0046] H. Iterative training: Perform multiple iterations on the training set, each time using batch data for training.

[0047] S104, collecting the communication data packets sent by the electric energy meter communication module in real time, and obtaining the state of the electric energy meter communication module in combination with the state detection model corresponding to the historical data packet closest to its length; assuming that there are two types of historical data packet lengths closest to the length of the communication data packet collected in real time, select the state detection model corresponding to the historical data packet with a smaller length than the communication data packet collected in real time to detect the electric energy meter communication module.

[0048] For example: assuming that the length of the communication data packet sent by the real-time electric energy meter communication module is 5, and the historical data packets collected in step S101 include historical data packets with a length of 4, historical data packets with a length of 5, and historical data packets with a length of 6, then the state detection model corresponding to the historical data packet with a length of 5 is selected as the current state detection model, and the communication data packet sent by the real-time electric energy meter communication module is input into the current state detection model to obtain the state of the electric energy meter communication module.

[0049] Assuming that there are two types of historical data packet lengths closest to the length of the real-time collected communication data packet, a state detection model corresponding to a historical data packet with a smaller length than the real-time collected communication data packet is selected to detect the electric energy meter communication module.

[0050] For example: assuming that the length of the communication data packet sent by the real-time electric energy meter communication module is 3, and the historical data packets collected in step S1 include historical data packets of length 2 and length 4, the classification model corresponding to the communication data packet of length 2 is preferentially selected to detect the state of the electric energy meter communication module. Since the real-time data packet is 3 in length, it is closer to the data packet of length 2 in terms of the degree of environmental interference, and the model may be more easily adapted to such minor changes, thereby maintaining a good classification effect, while the data packet of length 4 may be greatly different from the real-time data packet in terms of the degree of environmental interference, and the model may need more adjustments to handle such changes, resulting in unstable classification results.

[0051] Since data packets of different lengths are subject to different degrees of environmental interference when the communication module is detected using data packets, if the same classification model is used to detect data packets of different lengths, the detection result accuracy will be poor. When constructing the classification model, the method of this embodiment constructs different classification models (i.e., clustering modeling) for historical data packets of different lengths. After the real-time communication data packet is collected, the classification model corresponding to the historical data packet with the length closest to the real-time communication data packet is selected to detect the state of the electric energy meter communication module (i.e., the most appropriate classification model is selected), thereby greatly improving the accuracy of the electric energy meter communication module state detection.

[0052] In addition, when training the classification model, the importance of different types of communication data for judging the status of the communication module is comprehensively considered to avoid the limitations of a single data source; furthermore, by correcting the loss function based on the degree of interference of environmental data and the importance of communication data for judging the status of the communication module, real-time environmental interference (such as sudden temperature changes) can be suppressed, thereby improving the classification accuracy of the model in complex environments.

[0053] In one embodiment, The method for calculating the degree of interference of the environment when the mth type of communication data corresponding to the data packet of the type length is used to judge the state of the communication module comprises: S201, calculate the The mth type of communication data corresponding to the data packet of the type length is used to judge the interference degree of the communication module state caused by temperature, humidity and voltage fluctuation; S202: Perform weighted summation on the degree of interference caused by temperature, the degree of interference caused by humidity, and the degree of interference caused by voltage fluctuation, thereby obtaining the first The mth type of communication data corresponding to the data packet of the type length is used to judge the interference degree of the environment when the state of the communication module is judged.

[0054] In this embodiment, when calculating the degree of interference of environmental data on communication data for determining the state of the electric energy meter communication module, the degree of interference of a single environmental factor on communication data for determining the state of the electric energy meter communication module is not considered. Instead, the degree of interference of temperature on communication data for determining the state of the electric energy meter communication module, the degree of interference of humidity on communication data for determining the state of the electric energy meter communication module, and the degree of interference of voltage fluctuation on communication data for determining the state of the electric energy meter communication module are comprehensively considered, thereby making the calculation result of the degree of interference of environmental data on communication data for determining the state of the electric energy meter communication module more accurate.

[0055] In one embodiment, The calculation expression for the degree of interference from the environment when the mth type of communication data corresponding to the data packet of the type length is used to judge the state of the communication module is: ; In the formula, For the The information carrying capacity of the environmental data sequence; Respectively The information carrying capacity of temperature sequence, humidity sequence and voltage fluctuation sequence under the data packets of different lengths, , and Respectively represent The mth type of communication data corresponding to the data packet of the type length is used to judge the interference degree of the communication module state caused by temperature, humidity and voltage fluctuation.

[0056] In this embodiment, when calculating the degree of interference of environmental data on the mth communication data in determining the state of the electric energy meter communication module, not only the degree of interference of multiple environmental data on the communication data in determining the state of the electric energy meter communication module is taken into account, but also the information carrying capacity of various environmental data is further taken into account. When environmental data with a larger information carrying capacity changes, the degree of interference to the state of the communication module is greater. When the weighted sum of the interference degrees corresponding to various environmental data is performed, the weight corresponding to the environmental data with a larger information carrying capacity is larger, and the weight corresponding to the environmental data with a smaller information carrying capacity is smaller, thereby further improving the degree of interference of environmental data on the mth communication data in determining the state of the electric energy meter communication module.

[0057] In one embodiment, The information carrying capacity of environmental data The calculation expression is: ; In the formula, For the The length of the data packet corresponding to The standard deviation of the environmental data series, For the The length of the data packet corresponding to Environmental data series and Pearson correlation coefficient of environmental data series, They represent temperature series, humidity series and voltage fluctuation series respectively.

[0058] No. The larger the standard deviation of the αth environmental data sequence, the greater the data fluctuation of the αth environmental data. The greater the information carrying capacity of the first environmental data; The smaller the standard deviation of the environmental data sequence, the smaller the data fluctuation of the αth environmental data. The smaller the information carrying capacity of the environmental data. Environmental data series and The larger the Pearson correlation coefficient of the αth environmental data sequence, the stronger the correlation between the αth environmental data sequence and the jth environmental data sequence, and the smaller the conflict between the αth environmental data and the jth environmental data (i.e. The smaller the value is), the more the same information is, the The smaller the information carrying capacity of the first environmental data is, the smaller the Environmental data series and The smaller the Pearson correlation coefficient of the environmental data series, the Environmental data series and The weaker the correlation of the environmental data series, the Environmental data and The greater the conflict of the environmental data (i.e. The larger the value is), the less the same information is. Therefore, the information carrying capacity calculation expression of the environmental data of this embodiment can make the calculation result of the information carrying capacity of the environmental data more accurate.

[0059] In one embodiment, The calculation expression for the degree of interference of temperature when judging the state of the communication module by the mth type of communication data corresponding to the data packet of the type length is: ; In the formula, and Respectively The maximum and minimum values ​​in the mth communication data sequence corresponding to the data packet of the length, and Respectively The maximum and minimum values ​​of the temperature in the temperature sequence under the data packet of the same length. is the hyperbolic tangent function, For the The absolute value of the Pearson correlation coefficient between the temperature sequence under the data packet of the mth length and the mth communication data sequence.

[0060] is the ratio of the change in the mth communication data to the temperature change range. The larger the value, the higher the The larger the average fluctuation of the mth communication data when the temperature changes by 1°C under the data packet of the same length, the greater the interference of temperature on the mth communication data in judging the state of the electric energy meter communication module. The smaller the value, the greater the average fluctuation of the mth communication data when the temperature changes by 1°C. The smaller the average fluctuation amplitude of the mth communication data when the temperature changes by 1°C under the data packet of the same length, the smaller the interference degree of temperature on the mth communication data in judging the state of the communication module of the electric energy meter is. The larger the value, the more relevant the change of the temperature sequence under the i-th length data packet is to the m-th communication data sequence, and the greater the degree of interference of the temperature on the m-th communication data in judging the state of the electric energy meter communication module. The smaller the value, the less relevant the change of the temperature sequence under the i-th length data packet is to the m-th communication data sequence, and the smaller the degree of interference of the temperature on the m-th communication data in judging the state of the electric energy meter communication module. When calculating the degree of interference of the temperature on the m-th communication data in judging the state of the electric energy meter communication module, this embodiment takes into account the relationship between the ratio of the change amount of the m-th communication data to the temperature change range and the degree of interference corresponding to the temperature, as well as the relationship between the correlation between the temperature sequence and the m-th communication data sequence and the degree of interference corresponding to the temperature, so that the calculated degree of interference of the temperature on the m-th communication data in judging the state of the electric energy meter communication module is more accurate.

[0061] The interference degree of humidity on the mth communication data to judge the state of the energy meter communication module , and the interference degree of voltage fluctuation on the mth communication data to judge the state of the energy meter communication module With the The calculation method is the same.

[0062] In one embodiment, The length of the data packet corresponding to The importance of the mth communication data and the information gain of the mth communication data corresponding to the i-th length data packet for judging the state of the electric energy meter communication module is positively correlated, and the calculation expression of the information gain is: ; In the formula, is the information entropy of the state 𝑦 of the electric energy meter communication module under the 𝑖th length data packet; is the conditional entropy of the communication module state y of the energy meter after the mth communication data is known under the i-th length data packet.

[0063] In this embodiment, the With the equal, or the With the is directly proportional, and the proportionality coefficient is positive.

[0064] The larger the information gain, the The higher the importance of the mth communication data to the state judgment of the electric energy meter communication module under the data packet of the same length, the smaller the information gain is, indicating that the The importance of the mth type of communication data to the state judgment of the electric energy meter communication module is lower under the data packet of the same length. Therefore, the method of this embodiment can improve the calculated mth type of communication data. The accuracy of the importance of this communication data in determining the status of the electric energy meter communication module.

[0065] In one embodiment, the method further includes: performing linear interpolation processing on the collected historical data packets and environmental data, and performing wavelet transformation to remove noise therefrom.

[0066] By performing linear interpolation on the collected historical data packets and environmental data, missing values ​​can be filled. By using wavelet transform to denoise the collected data, the accuracy of the collected data can be improved, thereby further improving the accuracy of the status detection results of the electric energy meter communication module.

[0067] Embodiment of the electric energy meter communication module state detection system based on data analysis: The present invention also provides a power meter communication module status detection system based on data analysis. Figure 2 As shown, the electric energy meter communication module status detection system based on data analysis includes a processor and a memory, and the memory stores computer program instructions for detecting the status of the electric energy meter communication module. When the computer program instructions are executed by the processor, an electric energy meter communication module status detection method based on data analysis described in the above embodiment is implemented.

[0068] The data analysis-based electric energy meter communication module status detection system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface, whose settings and functions are known in the art and will not be described in detail here.

[0069] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0070] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A method for detecting the state of an electric energy meter communication module based on data analysis, characterized in that: include: Collect historical data packets of various lengths from the communication modules of electric energy meters, as well as environmental data at historical moments corresponding to each historical data packet; There are multiple historical data packets of each length; For each length of historical data packets, obtain the degree of interference from the environment when judging the state of the communication module for each communication data, as well as the importance of various communication data for judging the state of the communication module; build a classification model, train it using the loss function to obtain a state detection model, and the loss function calculation expression used when training the classification model corresponding to the i-th length data packet is: In the formula, For the The classification loss function of the nth communication data in the classification model corresponding to the data packet of this length; For the The label of the communication module status corresponding to the secondary communication data; is the output of the classification model Prediction of communication data probability; For the The mth type of communication data corresponding to the data packet of the type length determines the interference degree of the environment when the state of the communication module is judged; For the The length of the data packet corresponding to The importance of the communication data for determining the state of the communication module; The communication data packets sent by the electric energy meter communication module are collected in real time, and the state of the electric energy meter communication module is obtained by combining the state detection model corresponding to the historical data packet closest to its length; assuming that there are two types of historical data packet lengths closest to the length of the communication data packet collected in real time, the state detection model corresponding to the historical data packet with a smaller length than the communication data packet collected in real time is selected to detect the electric energy meter communication module.

2. The method for detecting the state of an electric energy meter communication module based on data analysis according to claim 1, characterized in that: No. The method for calculating the degree of interference of the environment when judging the state of the communication module by the mth type of communication data corresponding to the data packet of the type length comprises: calculating the mth type of communication data corresponding to the data packet of the type length The mth type of communication data corresponding to the data packet of the type length is used to judge the interference degree of the communication module state caused by temperature, humidity and voltage fluctuation; The interference degree due to temperature, the interference degree due to humidity and the interference degree due to voltage fluctuation are weighted and summed to obtain the first The mth type of communication data corresponding to the data packet of the type length is used to judge the interference degree of the environment when the state of the communication module is judged.

3. The method for detecting the state of an electric energy meter communication module based on data analysis according to claim 2, characterized in that: No. The calculation expression for the degree of interference from the environment when the mth type of communication data corresponding to the data packet of the type length is used to judge the state of the communication module is: ； In the formula, For the The information carrying capacity of the environmental data sequence; Respectively The information carrying capacity of temperature sequence, humidity sequence and voltage fluctuation sequence under the data packets of different lengths, , and Respectively represent The mth type of communication data corresponding to the data packet of the type length is used to judge the interference degree of the communication module state caused by temperature, humidity and voltage fluctuation.

4. The method for detecting the state of an electric energy meter communication module based on data analysis according to claim 3, characterized in that: No. The information carrying capacity of environmental data The calculation expression is: ； In the formula, For the The length of the data packet corresponding to The standard deviation of the environmental data series, For the The length of the data packet corresponding to Environmental data series and Pearson correlation coefficient of environmental data series, They represent temperature series, humidity series and voltage fluctuation series respectively.

5. The method for detecting the state of an electric energy meter communication module based on data analysis according to claim 3, characterized in that: No. The calculation expression for the degree of interference of temperature when judging the state of the communication module by the mth type of communication data corresponding to the data packet of the type length is: ； In the formula, and Respectively The maximum and minimum values ​​in the mth communication data sequence corresponding to the data packet of the length, and Respectively The maximum and minimum values ​​of the temperature in the temperature sequence under the data packet of the same length. is the hyperbolic tangent function, For the The absolute value of the Pearson correlation coefficient between the temperature sequence under the data packet of the mth length and the mth communication data sequence.

6. The method for detecting the state of an electric energy meter communication module based on data analysis according to claim 1, characterized in that: No. The length of the data packet corresponding to The importance of the mth communication data and the information gain of the mth communication data corresponding to the i-th length data packet for judging the state of the electric energy meter communication module is positively correlated, and the calculation expression of the information gain is: ； In the formula, is the information entropy of the state 𝑦 of the electric energy meter communication module under the 𝑖th length data packet; It is the conditional entropy of the state y of the electric energy meter communication module after the mth communication data is known under the i-th length data packet.

7. The method for detecting the state of an electric energy meter communication module based on data analysis according to claim 1, characterized in that: The communication data includes communication time, signal strength and packet loss rate.

8. The method for detecting the state of an electric energy meter communication module based on data analysis according to claim 1, characterized in that: The method also includes: performing linear interpolation processing on the collected historical data packets and environmental data, and performing denoising on the data by using wavelet transform.

9. The method for detecting the state of an electric energy meter communication module based on data analysis according to any one of claims 1 to 8, characterized in that: The classification model is a neural network model or a machine learning model.

10. A power meter communication module status detection system based on data analysis, characterized in that: It comprises a processor and a memory, wherein the memory stores computer program instructions for detecting the state of an electric energy meter communication module, and when the computer program instructions are executed by the processor, the electric energy meter communication module state detection method based on data analysis as described in any one of claims 1 to 9 is implemented.

Images