Remote monitoring method and system based on Internet of Things

Abstract

The invention relates to the field of monitoring and early warning, in particular to a remote monitoring method and system based on the Internet of Things. The method comprises the following steps: acquiring a plurality of operation index data points of a machine; clustering iteration training of the SOM algorithm is completed by using the operation index data points, and operation monitoring is realized; in any clustering training stage, acquiring an activated neuron in the current clustering training stage, and acquiring a data set of each neuron in each clustering training stage in the reference clustering training stage; obtaining fuzzy neurons according to an intersection relationship between the data set of the current clustering training stage of the activated neurons and the data sets of the reference training stages of other neurons; calculating the learning rate of each fuzzy neuron; and performing updating training on the fuzzy neurons and the activated neurons according to the learning rate. And the accuracy of clustering is improved by accurately updating the neurons, so that the monitoring accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the field of monitoring and early warning, and in particular to a remote monitoring method and system based on the Internet of Things. Background Art

[0002] With the development of science and technology, the level of intelligence of machines is getting higher and higher, and enterprises are increasingly advocating unmanned management of machines. However, it is inevitable that machines will have abnormalities during operation. If the abnormalities cannot be detected in time, it will lead to a series of subsequent problems; for example, if the reactor has an abnormality, the produced compound does not meet the quality requirements, and the compound can only be treated as a defective product at a low price, resulting in a waste of resources.

[0003] In order to understand the operation status of the machine in time, the operation status of the machine needs to be monitored. Since the operation index data generated when the machine is running abnormally is different from the operation index data generated when it is running normally, it is possible to judge whether the machine is in an abnormal state by screening outliers. Since the machine has multiple control states, and the operation index data corresponding to each control state is different, when judging the operation status of the machine by screening outliers, outliers are often misjudged due to differences in control states, thereby misjudging the normal operation of the machine as abnormal operation. In order to solve this problem, the operation index data needs to be clustered. The self-organizing map neural network algorithm (SOM) is often used for data clustering processing. This algorithm selects activated neurons by the similarity or distance between data and neurons, and then uses data to update and train the activated neurons until the neurons converge and update training is completed, and then it can be used for clustering processing. However, the neurons are not stable during the training phase, and the nearest neurons or most similar neurons of the data at different stages are different, which results in different activated neurons selected at different stages using the similarity or distance between the data and the neurons. If the data only updates the activated neurons, the neurons of the real category will not be updated, which leads to unsatisfactory training results of the SOM algorithm. Therefore, how to select the neurons that need to be updated and update and control the neurons that need to be updated becomes the research focus of the present invention.

[0004] The patent application document with publication number CN101846995A discloses a method for remote monitoring of industrial sites. The method in the patent application document mainly demonstrates the monitoring process. The anomaly detection involved in the monitoring process is merely the application of the existing anomaly detection algorithm, and does not involve the content of SOM neuron update control. Therefore, the method in the patent application document cannot solve the technical problems in this solution. Summary of the invention

[0005] In order to solve the problem of how to screen out neurons that need to be updated and perform update control on the neurons that need to be updated, the present invention provides a remote monitoring method and system based on the Internet of Things.

[0006] In a first aspect, the present invention provides a remote monitoring method based on the Internet of Things, which adopts the following technical solution: A remote monitoring method based on the Internet of Things comprises the following steps: Obtaining several operating indicator data points of the reactor; Use the operation indicator data points to complete the clustering iterative training of the SOM algorithm to achieve operation monitoring; In any cluster training stage, the activated neurons of the current cluster training stage are obtained, and the previous preset number of cluster training stages are obtained and recorded as reference cluster training stages. The operation index data points are divided into the data sets of the corresponding neurons according to the distance between each operation index data point and the neuron in each cluster training stage; the fuzzy neurons are obtained according to the intersection relationship between the data set of the current cluster training stage of the activated neurons and the data sets of the reference training stage of other neurons; Calculate the learning rate of each fuzzy neuron , , represents the number of data points in the intersection of the data set of the i-th reference cluster training stage of the k-th fuzzy neuron and the current cluster training stage of the activated neuron, N represents the preset number, represents the number of data points in the dataset for the current cluster training phase that activated the neuron, , They represent the distances between the running indicator data points of cluster training and the activated neurons and the kth fuzzy neuron used in the current cluster training phase, respectively. Respectively represent the position change variance of the kth fuzzy neuron and the activated neuron in all reference cluster training stages, Represents the preset learning rate for activating neurons; The fuzzy neurons and activation neurons are updated and trained according to the learning rate.

[0007] The present invention takes into account that when neurons are unstable, the activated neurons screened out in the current training stage are not necessarily the cluster centers to which the data belongs. Any neurons that have an intersection relationship with the data set of the activated neurons may become the cluster centers to which the data points belong. Therefore, by analyzing the intersection relationship between each neuron and the data set of the activated neurons in different training stages, the fuzzy neurons that may become the cluster centers of the data points are accurately screened out, providing a basis for accurately updating the neurons; further, by analyzing the possibility that each fuzzy neuron is the cluster center of the data point, the learning rate when the data point updates each fuzzy neuron is accurately calculated; further, when analyzing the possibility that each fuzzy neuron is the cluster center of the data point, the number of intersection data points of the data set of the fuzzy neuron and the activated neuron is introduced to accurately reflect the possibility that the data point flows to the category of the fuzzy neuron, and then accurately reflects the possibility that each fuzzy neuron is the cluster center of the data point; further, when analyzing the possibility that each fuzzy neuron is the cluster center of the data point, the distance from the data point to the fuzzy neuron is introduced to accurately reflect the possibility that the data point is called the category of the fuzzy neuron, and then accurately reflects the possibility that each fuzzy neuron is the cluster center of the data point.

[0008] Preferably, the step of dividing the operation index data points into data sets corresponding to neurons according to the distance between each operation index data point and the neuron in each cluster training stage comprises: In each cluster training stage, the distance between each operation index data point and each neuron is obtained, and each operation index data point is divided into the data set of the neuron closest to it, so as to obtain the data set of each neuron in each cluster training stage.

[0009] The present invention divides data points into data sets corresponding to neurons through distance relationships. This implementation method is relatively simple and has higher implementation efficiency.

[0010] Preferably, the method of obtaining a fuzzy neuron according to the intersection relationship between the data set of the current cluster training phase of the activated neuron and the data set of the reference training phase of other neurons includes: If the data set of the current cluster training phase of the activated neuron intersects with the data set of the reference cluster training phase of other neurons, the other neurons are recorded as suspected fuzzy neurons; The data points in the data set of the current cluster training phase where activated neurons exist and in the data set of the reference training phase where fuzzy neurons exist are recorded as jump data points; Calculate the abnormal probability of the jumping data point; record the jumping data point whose abnormal probability is less than the preset probability threshold as the target jumping data point; The suspected fuzzy neurons with target jump data points in the data set of the reference cluster training phase are recorded as fuzzy neurons.

[0011] The present invention accurately screens out fuzzy neurons that may become clustering centers of data points by analyzing the intersection relationship between each neuron and the data set of activated neurons in different training stages; further, considering that abnormal data points may also jump between corresponding categories of different neurons, and this jump is not caused by insufficient neuron updating, it is necessary to eliminate the interference of abnormal data points in the intersection relationship and accurately extract fuzzy neurons.

[0012] Preferably, the calculating of the abnormal possibility of the jumping data point includes: Obtain the unilateral neighborhood data points of the jumping data point; record the mean distance between the jumping data point and the unilateral neighborhood data points as the metric distance, and determine the normalized value of the ratio of the metric distance of the jumping data point to the mean metric distance of all running indicator data points as the abnormal possibility of the jumping data point.

[0013] The present invention eliminates the influence of other types of neighborhood data on distance calculation by introducing a single biased neighborhood data point, and relatively accurately analyzes the abnormal situation of the data point.

[0014] Preferably, the step of obtaining a single biased neighborhood data point of a jumping data point includes: The area within the preset radius of the jump data point is recorded as a preset neighborhood, and the operation indicator data points within the preset neighborhood are recorded as neighborhood data points; the preset neighborhood is evenly divided into a preset number of areas with the jump data point as the center; Calculate the mean of the distance between the neighborhood data points and the jump data points in each region and record it as the distance of the region; The neighborhood data points in the area whose distance is less than the mean of the distances of all areas are regarded as unilateral neighborhood data points.

[0015] The present invention analyzes the data points in the neighborhood by region, accurately screens out data points of other categories, and provides a basis for accurate anomaly analysis.

[0016] Preferably, the method for obtaining the position change variance includes: The position of each neuron in each cluster reference stage is obtained, the distance between the positions of each neuron in the two reference cluster training stages is calculated, and the variance of the position distance of each neuron in all two reference cluster training stages is recorded as the variance of the position change of the neuron in all reference cluster training stages.

[0017] Preferably, the implementation of operation monitoring includes: Input the newly collected operation index data points of the reactor into the SOM algorithm after cluster training to obtain the category to which the newly collected operation index data points belong; obtain the lower quartile of the distance between each operation index data point and the cluster center of the category to which it belongs; Obtaining the distance between the newly collected operation index data point and the cluster center of the category to which it belongs. If the distance between the newly collected operation index data point and the cluster center of the category to which it belongs is greater than the lower quartile, determining that the newly collected operation index data point is an abnormal data point; If the number of continuously collected abnormal data points is greater than a preset number threshold, it is determined that the reactor operation is abnormal.

[0018] In a second aspect, the present invention provides a remote monitoring system based on the Internet of Things, which adopts the following technical solutions: A remote monitoring system based on the Internet of Things comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned remote monitoring method based on the Internet of Things is implemented.

[0019] By adopting the above technical solution, the above-mentioned remote monitoring method based on the Internet of Things is generated into a computer program and stored in a memory to be loaded and executed by a processor, so that a terminal device is made according to the memory and the processor for easy use.

[0020] The present invention has the following technical effects: The present invention takes into account that when neurons are unstable, the activated neurons selected in the current training stage are not necessarily the cluster centers to which the data belongs. Any neurons that have an intersection relationship with the data set of the activated neurons may become the cluster center to which the data points belong. Therefore, by analyzing the intersection relationship between each neuron and the data set of the activated neurons in different training stages, the fuzzy neurons that may become the cluster centers of the data points are accurately selected, providing a basis for accurately updating neurons. Furthermore, by analyzing the possibility that each fuzzy neuron is the cluster center of the data point, the learning rate when the data point updates each fuzzy neuron is accurately calculated; Furthermore, when analyzing the possibility that each fuzzy neuron is the cluster center of the data points, the number of intersection data points of the data sets of the fuzzy neuron and the activated neuron is introduced to accurately reflect the possibility that the data points flow to the category to which the fuzzy neuron belongs, thereby accurately reflecting the possibility that each fuzzy neuron is the cluster center of the data points; Furthermore, when analyzing the possibility that each fuzzy neuron is the cluster center of the data point, the distance from the data point to the fuzzy neuron is introduced to accurately reflect the possibility that the data point becomes the category to which the fuzzy neuron belongs, thereby accurately reflecting the possibility that each fuzzy neuron is the cluster center of the data point. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0022] Figure 1 The present invention is a flowchart of a remote monitoring method based on the Internet of Things in 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] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0025] The embodiment of the present invention discloses a remote monitoring method based on the Internet of Things, referring to Figure 1 , comprising steps S1-S2: S1: Obtain several operating indicator data points of the machine.

[0026] Specifically, each type of operating index data of the machine at each moment is obtained. In this embodiment, the machine is a reactor as an example of a monitoring object. Other embodiments can be replaced with other monitoring objects, and this embodiment does not specifically limit it. When the reactor is used as the monitoring object, the types of operating index data mainly collected include but are not limited to the following aspects: temperature, pressure, liquid level, stirring speed and flow rate.

[0027] S2: Use the operation indicator data points to complete the clustering iterative training of the SOM algorithm to achieve operation monitoring.

[0028] S20: Use the running indicator data points to complete the clustering iterative training of the SOM algorithm.

[0029] S200: In any clustering training stage, the activated neurons of the current clustering training stage are obtained, and the previous preset number of clustering training stages are obtained and recorded as reference clustering training stages. The operation indicator data points are divided into data sets of corresponding neurons according to the distance between each operation indicator data point and the neuron in each clustering training stage; the fuzzy neurons are obtained according to the intersection relationship between the data set of the current clustering training stage of the activated neurons and the data sets of the reference training stage of other neurons.

[0030] It should be noted that when neurons are unstable, the data attached to different neurons will switch back and forth in different training stages. In other words, some data have not yet determined which neuron is its cluster center, resulting in some data being attached to one neuron in some training stages and to another neuron in the next training stage. Therefore, in each training stage, it is not accurate to only update the activated neurons. Therefore, it is necessary to determine which neurons are its possible cluster centers, and then update all possible cluster centers.

[0031] First, in any clustering training stage, the activated neurons of the current clustering training stage are obtained, and the previous preset number of clustering training stages are obtained and recorded as reference clustering training stages. The operating indicator data points are divided into the data sets of corresponding neurons according to the distance between each operating indicator data point and the neurons in each clustering training stage.

[0032] Preferably, as an example, in any cluster training stage, the activated neurons in the current cluster training stage are obtained, the previous preset number of cluster training stages are obtained and recorded as reference cluster training stages, and the operation index data points are divided into data sets of corresponding neurons according to the distance between each operation index data point and the neuron in each cluster training stage, including: In any cluster training stage, the activated neurons of the current cluster training stage are obtained, and the previous preset number of cluster training stages are obtained and recorded as reference cluster training stages. This embodiment is described by taking the preset number of 5 as an example, and other embodiments may take other values, which are not specifically limited in this embodiment.

[0033] The distance between each operation index data point and each neuron in each cluster training stage is obtained, and each operation index data point is divided into a data set of a neuron closest to it, so as to obtain a data set of each neuron in each cluster training stage.

[0034] It should be noted that the data points in the data set of each neuron in each cluster training stage are the attached data points of each neuron in each cluster training stage.

[0035] It should be further explained that the method for obtaining the activated neurons in the current cluster training stage is a prior art and will not be described in detail here.

[0036] Then, in any cluster training stage, the fuzzy neuron is obtained according to the intersection relationship between the data set of the current cluster training stage of the activated neuron and the data set of the reference training stage of other neurons.

[0037] It should be noted that in different training stages, there will be switching of attached data points between some neurons, which means that the attached data will flow back and forth in these neurons, which means that these neurons are likely to be the clustering centers of the data. Therefore, when the data updates the neurons, these neurons need to be updated. Therefore, the interfering neurons of neurons can be determined based on the switching relationship of the attached data points of different neurons.

[0038] It should be further explained that some data cannot be accurately classified into which neuron data set because some data are abnormal data, which causes the data to switch back and forth between different neurons. This is caused by the data, not by the instability of neurons, so the influence of such data on the acquisition of interfering neurons needs to be excluded.

[0039] Preferably, as an example, in any cluster training stage, a fuzzy neuron is obtained according to the intersection relationship between the data set of the current cluster training stage of the activated neuron and the data set of the reference training stage of other neurons, including: If the data set of the current cluster training phase of the activated neuron intersects with the data set of the reference cluster training phase of other neurons, the other neurons are recorded as suspected fuzzy neurons; The data points in the data set of the current cluster training phase where activated neurons exist and in the data set of the reference training phase where fuzzy neurons exist are recorded as jump data points; Calculate the abnormal probability of the jumping data point; record the jumping data point whose abnormal probability is less than the preset probability threshold as the target jumping data point; in this embodiment, the preset probability threshold is 0.85 as an example for description, and other embodiments may take other values, which are not specifically limited in this embodiment.

[0040] The suspected fuzzy neurons with target jump data points in the data set of the reference cluster training phase are recorded as fuzzy neurons.

[0041] It should be noted that fuzzy neurons are neurons that have attached data switching with activated neurons. The data is attached to the activated neurons in the current training stage and may be attached to the fuzzy neurons in the subsequent training stage. Therefore, in the current training stage, it cannot be determined whether the fuzzy neurons or the activated neurons are the clustering centers of the data. Therefore, the data needs to be updated for both the fuzzy neurons and the activated neurons.

[0042] The above embodiments involve the abnormal possibility of jumping data points. The following is an explanation of the method for calculating the abnormal possibility of jumping data points.

[0043] Optionally, as an example, calculate the anomaly probability of the jumping data point, including: The operation index data points within the preset radius of the jump data point are recorded as neighborhood data points; this embodiment is described by taking the preset radius of 20 as an example, other embodiments may take other values, and this embodiment does not make specific restrictions.

[0044] Calculate the mean of the distance between the neighborhood data points and the jump data points, and record it as the neighborhood distance of the jump data points; The neighborhood distances of other operating indicator data points are calculated, and the normalized data of the ratio of the neighborhood distance of the jumping data point to the mean of the neighborhood distances of all other operating indicator data points is used as the abnormal possibility of the jumping data point.

[0045] It should be noted that since some jump data points are at the classification boundary, there may be data points of other categories in the neighborhood of the jump data points, and it is normal for the jump data points to be far away from the data points of other categories. However, the large distance between the jump data points and the data points of other categories will lead to a greater possibility of abnormal calculation of the jump data points. Therefore, it is easy to misjudge the jump data points at the classification boundary as abnormal data points in this way, and thus it is impossible to accurately exclude the influence of abnormal data points on interfering with neuron acquisition.

[0046] Preferably, as an example, calculating the abnormal possibility of the jumping data point includes: The area within the preset radius of the jumping data point is recorded as the preset neighborhood, and the operation index data points within the preset neighborhood are recorded as neighborhood data points; the preset neighborhood is evenly divided into a preset number of areas with the jumping data point as the center; this embodiment is described by taking the preset number of 30 as an example, other embodiments may take other values, and this embodiment does not make specific restrictions.

[0047] Calculate the mean of the distance between the neighborhood data points and the jump data points in each region and record it as the distance of the region; The neighborhood data points in the area whose distance is less than the mean of the distances of all areas are regarded as unilateral neighborhood data points.

[0048] The mean distance between the jumping data point and the unilateral neighboring data points is recorded as the metric distance, and the normalized value of the ratio of the metric distance of the jumping data point to the mean metric distance of all running indicator data points is determined as the abnormal possibility of the jumping data point.

[0049] It should be noted that by dividing the area to exclude other categories of data in the neighborhood, the distance relationship between the jumping data points and other surrounding data points can be accurately measured, thereby relatively accurately reflecting the abnormal situation of the jumping data, and then relatively accurately excluding the influence of abnormal data points on interfering neuron acquisition.

[0050] S201: Calculate the learning rate of each fuzzy neuron.

[0051] It should be noted that the above process has screened out the neurons that need to be updated, and the following needs to control the update of each neuron that needs to be updated. The learning rate is used to determine the update degree of each neuron, so the update control of each neuron that needs to be updated is performed by adjusting the learning rate.

[0052] Preferably, as an example, calculating the learning rate of each fuzzy neuron includes:

[0053] in, represents the number of data points in the intersection of the data set of the i-th reference cluster training stage of the k-th fuzzy neuron and the current cluster training stage of the activated neuron, N represents the preset number, represents the number of data points in the dataset for the current cluster training phase that activated the neuron, Indicates the distance between the running indicator data point of cluster training and the activated neuron used in the current cluster training stage, Indicates the distance between the running indicator data point of cluster training used in the current cluster training phase and the kth fuzzy neuron, represents the position change variance of the kth fuzzy neuron in all reference cluster training stages, represents the variance of the position change of activated neurons in all reference cluster training stages, represents the preset learning rate for activating neurons, Represents the learning rate of the kth fuzzy neuron.

[0054] Understandably, It reflects the possibility that the fuzzy neuron is the cluster center of the data used for cluster training in the current cluster training stage. The larger the value, the more the data needs to be used to update the fuzzy neuron, so as to locate each cluster center more accurately. It reflects the relative distance between the data used for cluster training and the fuzzy neurons and activated neurons in the current cluster training stage. The larger the value, the closer the data used for cluster training is to the fuzzy neurons, and the more the data should be used to update the fuzzy neurons. It reflects the stability of the fuzzy neuron. The larger the value, the more unstable the fuzzy neuron is and the more it needs to be updated. Therefore, the larger the learning rate should be. It reflects the necessity of updating the fuzzy neuron compared with the activated neuron. The learning rate of the fuzzy neuron can be obtained by multiplying it by the preset learning rate of the activated neuron.

[0055] It should be added that the method for obtaining the position change variance includes: The position of each neuron in each cluster reference stage is obtained, the distance between the positions of each neuron in the two reference cluster training stages is calculated, and the variance of the position distance of each neuron in all two reference cluster training stages is recorded as the variance of the position change of the neuron in all reference cluster training stages.

[0056] S202: Performing update training on the fuzzy neurons and activated neurons according to the learning rate.

[0057] It should be noted that updating and training fuzzy neurons and activated neurons according to the learning rate is an existing technology and will not be described in detail here.

[0058] S21: Implement operation monitoring.

[0059] Preferably, as an example, the operation monitoring is implemented, including: Input the newly collected operation index data points of the reactor into the SOM algorithm after cluster training to obtain the category to which the newly collected operation index data points belong; obtain the lower quartile of the distance between each operation index data point and the cluster center of the category to which it belongs; Obtaining the distance between the newly collected operation index data point and the cluster center of the category to which it belongs. If the distance between the newly collected operation index data point and the cluster center of the category to which it belongs is greater than the lower quartile, determining that the newly collected operation index data point is an abnormal data point; If the number of abnormal data points collected continuously is greater than the preset number threshold, it is determined that the reactor is abnormal, and the relevant personnel are notified to make adjustments. This embodiment takes the preset number threshold of 5 as an example for description, and other embodiments may take other values, which are not specifically limited in this embodiment.

[0060] An embodiment of the present invention further discloses a remote monitoring system based on the Internet of Things, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a remote monitoring method based on the Internet of Things according to the present invention is implemented.

[0061] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0062] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory, a dynamic random access memory, a static random access memory, an enhanced dynamic random access memory, a high bandwidth memory, a hybrid storage cube, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0063] 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.

[0064] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A remote monitoring method based on the Internet of Things, characterized in that: Includes steps: Obtaining several operating indicator data points of the reactor; Use the operation indicator data points to complete the clustering iterative training of the SOM algorithm to achieve operation monitoring; In any cluster training stage, the activated neurons of the current cluster training stage are obtained, and the previous preset number of cluster training stages are obtained and recorded as reference cluster training stages. The operation index data points are divided into the data sets of the corresponding neurons according to the distance between each operation index data point and the neuron in each cluster training stage; the fuzzy neurons are obtained according to the intersection relationship between the data set of the current cluster training stage of the activated neurons and the data sets of the reference training stage of other neurons; Calculate the learning rate of each fuzzy neuron , , represents the number of data points in the intersection of the data set of the i-th reference cluster training stage of the k-th fuzzy neuron and the current cluster training stage of the activated neuron, N represents the preset number, represents the number of data points in the dataset for the current cluster training phase that activated the neuron, , They represent the distances between the running indicator data points of cluster training and the activated neurons and the kth fuzzy neuron used in the current cluster training phase, respectively. Respectively represent the position change variance of the kth fuzzy neuron and the activated neuron in all reference cluster training stages, Represents the preset learning rate for activating neurons; The fuzzy neurons and activation neurons are updated and trained according to the learning rate.

2. The remote monitoring method based on the Internet of Things according to claim 1, characterized in that: The step of dividing the operation index data points into data sets corresponding to neurons according to the distances between the operation index data points and neurons in each cluster training stage includes: In each cluster training stage, the distance between each operation index data point and each neuron is obtained, and each operation index data point is divided into the data set of the neuron closest to it, so as to obtain the data set of each neuron in each cluster training stage.

3. The remote monitoring method based on the Internet of Things according to claim 1, characterized in that: The method of obtaining a fuzzy neuron according to the intersection relationship between the data set of the current cluster training phase of the activated neuron and the data set of the reference training phase of other neurons includes: If the data set of the current cluster training phase of the activated neuron intersects with the data set of the reference cluster training phase of other neurons, the other neurons are recorded as suspected fuzzy neurons; The data points in the data set of the current cluster training phase where activated neurons exist and in the data set of the reference training phase where fuzzy neurons exist are recorded as jump data points; Calculate the abnormal probability of the jumping data point; record the jumping data point whose abnormal probability is less than the preset probability threshold as the target jumping data point; The suspected fuzzy neurons with target jump data points in the data set of the reference cluster training phase are recorded as fuzzy neurons.

4. The remote monitoring method based on the Internet of Things according to claim 3 is characterized in that: The calculating of the abnormal possibility of the jumping data point includes: Obtain the unilateral neighborhood data points of the jumping data point; record the mean distance between the jumping data point and the unilateral neighborhood data points as the metric distance, and determine the normalized value of the ratio of the metric distance of the jumping data point to the mean metric distance of all running indicator data points as the abnormal possibility of the jumping data point.

5. The remote monitoring method based on the Internet of Things according to claim 4 is characterized in that: The step of obtaining a single biased neighborhood data point of a jumping data point includes: The area within the preset radius of the jump data point is recorded as a preset neighborhood, and the operation indicator data points within the preset neighborhood are recorded as neighborhood data points; the preset neighborhood is evenly divided into a preset number of areas with the jump data point as the center; Calculate the mean of the distance between the neighborhood data points and the jump data points in each region and record it as the distance of the region; The neighborhood data points in the area whose distance is less than the mean of the distances of all areas are regarded as unilateral neighborhood data points.

6. The remote monitoring method based on the Internet of Things according to claim 1, characterized in that: The method for obtaining the position change variance includes: The position of each neuron in each cluster reference stage is obtained, the distance between the positions of each neuron in the two reference cluster training stages is calculated, and the variance of the position distance of each neuron in all two reference cluster training stages is recorded as the variance of the position change of the neuron in all reference cluster training stages.

7. The remote monitoring method based on the Internet of Things according to claim 1, characterized in that: The implementation of operation monitoring includes: Input the newly collected operation index data points of the reactor into the SOM algorithm after cluster training to obtain the category to which the newly collected operation index data points belong; obtain the lower quartile of the distance between each operation index data point and the cluster center of the category to which it belongs; Obtaining the distance between the newly collected operation index data point and the cluster center of the category to which it belongs. If the distance between the newly collected operation index data point and the cluster center of the category to which it belongs is greater than the lower quartile, determining that the newly collected operation index data point is an abnormal data point; If the number of continuously collected abnormal data points is greater than a preset number threshold, it is determined that the reactor operation is abnormal.

8. A remote monitoring system based on the Internet of Things, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a remote monitoring method based on the Internet of Things according to any one of claims 1 to 7 is implemented.

Images