An industrial internet of things electromagnetic safety event rapid identification and processing method

Abstract

The present application relates to the technical field of data processing, and especially relates to a kind of industrial internet of things electromagnetic safety event fast identification and processing method, the method obtains the environment interference intensity under different operating environments according to electromagnetic signal quality and operating environment of industrial internet of things equipment in each operation period when no electromagnetic safety event occurs;Signal parameters for identifying electromagnetic safety events are obtained, and according to the operating state and environment interference intensity of industrial internet of things equipment in each operation period, the initial threshold interval of signal parameters is obtained;Whether electromagnetic safety event occurs in each historical period is re-identified using the initial threshold interval, and the false alarm rate and the false negative rate are obtained;The initial threshold interval is corrected according to the false alarm rate and the false negative rate, and the final threshold interval of signal parameters is obtained, and electromagnetic safety events are identified in real time according to the final threshold interval of signal parameters, which improves the accuracy of identifying electromagnetic safety events.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to an industrial internet of things electromagnetic safety event rapid identification and processing method. BACKGROUND

[0002] Industrial internet of things (IIoT) realizes real-time monitoring, data collection and intelligent decision-making of industrial production process by deeply integrating sensors, intelligent devices, industrial control systems and the Internet. However, industrial internet of things devices are usually deployed in complex electromagnetic environments such as high-voltage power grids, high-frequency devices, wireless communication base stations and other areas. In these environments, electromagnetic safety events such as electromagnetic interference (EMI), electromagnetic pulse (EMP) and malicious electromagnetic attacks (such as electromagnetic signal eavesdropping and device tampering) may cause physical damage or data leakage to industrial internet of things devices.

[0003] The identification of electromagnetic safety events in the prior art relies on fixed threshold detection (such as the 3sigma principle), manual inspection or post-event analysis, which lacks real-time and accuracy. For example, when industrial internet of things devices exhibit abnormalities due to electromagnetic interference, it is necessary to analyze logs or determine the cause of the abnormality in the offline state of the device, which cannot quickly locate the root cause of the problem. In addition, fixed threshold detection is difficult to adapt to changing industrial scenarios. For example, high temperatures may cause industrial internet of things devices to overheat, causing electromagnetic interference or failure. Changes in humidity can affect the insulation performance and electrical connections of industrial internet of things devices, thereby affecting the transmission and reception of electromagnetic signals. These environmental disturbances increase the volatility of electromagnetic signals, reduce the signal-to-noise ratio, increase the bit error rate, and increase the frame synchronization time. If fixed threshold detection is used, it may result in a high false positive rate and a high false negative rate for electromagnetic safety events.

[0004] Therefore, how to improve the accuracy of identifying electromagnetic safety events has become a problem to be solved. SUMMARY

[0005] Therefore, the embodiments of the present application provide an industrial internet of things electromagnetic safety event rapid identification and processing method to solve the problem of how to improve the accuracy of identifying electromagnetic safety events.

[0006] An industrial internet of things electromagnetic safety event rapid identification and processing method is provided in the embodiments of the present application, which includes the following steps:

[0007] Obtain at least two running time periods of the industrial internet of things device before the current running time period without electromagnetic safety events, and obtain the environmental disturbance intensity under the running environment in each running time period according to the quality of the electromagnetic signal in each running time period and the running environment of the industrial internet of things device in each running time period.

[0008] acquire any signal parameter used for identifying electromagnetic safety event, acquire initial threshold interval of the any signal parameter of the industrial internet of things device in the current operation period according to signal parameter value of the any signal parameter in each operation period, and operation state and environmental interference intensity of the industrial internet of things device in each operation period;

[0009] re-identify whether electromagnetic safety event occurs in at least two historical periods of the industrial internet of things device by using the initial threshold interval, and obtain false positive rate and false negative rate of the initial threshold interval for identifying electromagnetic safety event in the historical period;

[0010] correct the initial threshold interval according to the false positive rate and the false negative rate, obtain final threshold interval of the any signal parameter of the industrial internet of things device in the current operation period, and identify whether electromagnetic safety event occurs in the current operation period of the industrial internet of things device in real time according to the final threshold interval of each signal parameter of the industrial internet of things device in the current operation period.

[0011] Compared with the prior art, the embodiment of the present application has the beneficial effects that:

[0012] The application obtains at least two runtime periods of the industrial Internet of Things device before the current runtime period without electromagnetic safety events, obtains the environmental interference intensity in the running environment of each runtime period according to the quality of the electromagnetic signal in each runtime period and the running environment of the industrial Internet of Things device in each runtime period, obtains the initial threshold interval of any signal parameter for identifying electromagnetic safety events in the current runtime period of the industrial Internet of Things device according to the signal parameter value of the any signal parameter in each runtime period and the running state and the environmental interference intensity of the industrial Internet of Things device in each runtime period, re-identifies whether electromagnetic safety events occur in at least two historical periods by using the initial threshold interval, obtains the false alarm rate and the missed alarm rate of the initial threshold interval for identifying electromagnetic safety events in the historical period, corrects the initial threshold interval according to the false alarm rate and the missed alarm rate, obtains the final threshold interval of the any signal parameter of the industrial Internet of Things device in the current runtime period, and identifies in real time whether electromagnetic safety events occur in the current runtime period of the industrial Internet of Things device according to the final threshold interval of each signal parameter of the industrial Internet of Things device in the current runtime period. Wherein, the environmental interference intensity in different environments and the different running states of the industrial Internet of Things device are comprehensively considered to adaptively set the initial threshold interval of the signal parameter for identifying electromagnetic safety events, then the initial threshold interval is used to re-identify the historical electromagnetic safety events, the accuracy of the initial threshold interval is detected to obtain the false alarm rate and the missed alarm rate for identifying electromagnetic safety events, and then the initial threshold interval is corrected according to the false alarm rate and the missed alarm rate to obtain the final threshold interval, so as to adapt to the changeable industrial scene and improve the accuracy of identifying electromagnetic safety events. BRIEF DESCRIPTION OF DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0014] Figure 1 It is a method flow chart of an industrial Internet of Things electromagnetic safety event rapid identification and processing method provided by the embodiment one of the present application. DETAILED DESCRIPTION

[0015] The embodiments of the present application will be described in detail below, and examples of the embodiments are shown in the drawings. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present application, and cannot be understood as a limitation of the present application.

[0016] It should be noted that the terms "first", "second", etc. in the specification of the present disclosure and the above drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The implementation described in the following exemplary embodiments does not represent all implementations consistent with the present disclosure. Instead, they are only examples of devices and methods consistent with some aspects of the present disclosure.

[0017] In order to illustrate the technical solutions of the present application, the following will be illustrated by specific embodiments.

[0018] Referring to Figure 1 , it is a method flow chart of an industrial Internet of Things electromagnetic safety event rapid identification and processing method provided by an embodiment of the present application, as Figure 1 shown, the method can include:

[0019] Step S101, obtaining at least two running time periods of the industrial Internet of Things device before the current running time period without electromagnetic safety events, obtaining the environmental disturbance intensity under the running environment in each running time period according to the quality of the electromagnetic signal in each running time period and the running environment of the industrial Internet of Things device in each running time period.

[0020] In the process of running the industrial Internet of Things device, through the antenna or electromagnetic induction device (such as Hall sensor), combined with signal conditioning and digital signal processing technology, the electromagnetic signal of the industrial Internet of Things device in at least two running time periods without electromagnetic safety events before the current running time period is obtained, the length of the running time period is set to 1s, which is not limited here, and the implementer can set it according to the specific industrial Internet of Things scene.

[0021] The identification of electromagnetic safety events under the prior art usually depends on fixed threshold intervals (such as 3sigma principle), which lacks real-time and accuracy, but the fixed threshold interval is difficult to adapt to the changing industrial scene, for example, too high temperature may cause the industrial Internet of Things device to overheat and cause electromagnetic interference or failure, humidity changes will affect the insulation performance and electrical connection of the industrial Internet of Things device, thereby affecting the transmission and reception of electromagnetic signals, these environmental disturbances affect the electromagnetic signal, resulting in a high false positive rate or false negative rate of electromagnetic safety events.

[0022] Therefore, in the embodiment of the present application, the interference intensity of the electromagnetic signal under different operating environments is obtained according to the electromagnetic signal quality and operating environment of the industrial Internet of Things device in each operating period, the threshold interval is adaptively set according to the interference intensity of the electromagnetic signal under different operating environments, and then whether an electromagnetic safety event occurs to the industrial Internet of Things device in the current operating period is identified according to the adaptively set threshold interval, thereby improving the accuracy of identifying the electromagnetic safety event.

[0023] Firstly, the electromagnetic signal with the least environmental interference is obtained in each operating period. When the industrial Internet of Things device is normally operated, the quality of the electromagnetic signal has the following characteristics: the signal intensity changes relatively smoothly, the signal-to-noise ratio is usually greater than 15 dB (greater than 20 dB in some high requirement scenarios), the bit error rate is lower than ( lower than in some key applications), the frame synchronization time is less than 10 ms, and so on. Therefore, the signal-to-noise ratio, the bit error rate and the frame synchronization time are used as quality parameters for determining the quality of the electromagnetic signal of the industrial Internet of Things device in each operating period.

[0024] For the electromagnetic signal in the i th operating period, the signal-to-noise ratio of the electromagnetic signal in the i th operating period is obtained by a spectrum analyzer or a self-correlation / cross-correlation algorithm, the bit error rate of the electromagnetic signal in the i th operating period is obtained by a BER formula based on the modulation mode, and the frame synchronization time of the electromagnetic signal in the i th operating period is obtained by a built-in time stamp or a hardware timer. It should be noted that according to the scene of the industrial Internet of Things device, the signal-to-noise ratio, the bit error rate and the frame synchronization time may need to be calculated once per second, or may need to be calculated multiple times per second (such as a high real-time system). If it needs to be calculated multiple times per second, the signal-to-noise ratio, the bit error rate and the frame synchronization time of the electromagnetic signal in the i th operating period are the mean values in the i th operating period. In the embodiment of the present application, the calculation frequency of the signal-to-noise ratio, the bit error rate and the frame synchronization time is set to be calculated once per second. The acquisition method of the signal-to-noise ratio, the bit error rate and the frame synchronization time is a prior art, which will not be described here. If the signal-to-noise ratio of the electromagnetic signal in the i th operating period is greater than 15 dB, the bit error rate is lower than , and the frame synchronization time is less than 10 ms, it indicates that the electromagnetic signal in the i th operating period is less disturbed by the environment. Therefore, the electromagnetic signal in the i th operating period is recorded as a target electromagnetic signal, and all target electromagnetic signals are obtained in the same way.

[0025] In addition to the signal-to-noise ratio being greater than 15 dB and the bit error rate being lower than , in addition to the frame synchronization time being less than 10 ms, the electromagnetic signal of the industrial Internet of Things device in normal operation should also satisfy the characteristic that the signal strength changes relatively smoothly, and parameters for measuring the signal strength include the power density, the magnetic field strength and the received power, etc., in the present application, the received power is taken as the target strength parameter of each target electromagnetic signal, here, no limitation is made, and the implementer can set other strength parameters as the target strength parameter according to the specific scene, taking the jth target electromagnetic signal as an example, the received power of every 10 ms in the operation period in which the jth target electromagnetic signal is located is obtained, and is denoted as the received power value (i.e., the strength value of the strength parameter), here, no limitation is made, and the implementer can set the acquisition frequency of the received power according to the specific scene, the standard deviation of all the received power values in the operation period in which the jth target electromagnetic signal is located is calculated, and is denoted as , the reciprocal of the sum of the constant 1 and the standard deviation is calculated, and the strength change stability index of the jth target electromagnetic signal is obtained, and is denoted as , that is, , The smaller the value is, the more concentrated the distribution of the received power values in the operation period in which the jth target electromagnetic signal is located is, The larger the value is, the more stable the signal strength change of the jth target electromagnetic signal is.

[0026] Similarly, the strength change stability indexes of all the target electromagnetic signals are obtained, in all the strength change stability indexes, the target electromagnetic signal corresponding to the maximum value is selected, and is denoted as a reference electromagnetic signal, which is used to represent the electromagnetic signal of the industrial Internet of Things device that is least disturbed by the environment in the operation process.

[0027] The electromagnetic signals in each operation period except the operation period in which the reference electromagnetic signal is located are denoted as other electromagnetic signals, since the electromagnetic signals in each operation period are all electromagnetic signals of the industrial Internet of Things device that do not occur electromagnetic safety events, to a great extent, the difference between each other electromagnetic signal and the reference electromagnetic signal is caused by the environmental interference. Therefore, in the embodiment of the present application, according to the signal quality difference and the strength change difference between each other electromagnetic signal and the reference electromagnetic signal, the signal deviation degree of each other electromagnetic signal is obtained, which is used to represent the difference between each other electromagnetic signal and the reference signal, so as to obtain the environmental interference intensity in the operation environment of each operation period according to the signal deviation degree of each other electromagnetic signal. Taking the kth other electromagnetic signal as an example, the specific way of obtaining the signal deviation degree of the kth other electromagnetic signal is as follows:

[0028] a quality difference value between the quality parameter value of each quality parameter (i.e. signal-to-noise ratio, bit error rate and frame synchronization time) of the kth other electromagnetic signal and the reference electromagnetic signal, and an intensity variation difference value between the intensity variation stability index of the kth other electromagnetic signal and the reference electromagnetic signal, linearly normalizing each of the quality difference value and the intensity variation difference value to obtain a normalized quality difference value of each of the quality difference value and a normalized intensity variation difference value of the intensity variation difference value, wherein linear normalization is a prior art and will not be described here;

[0029] calculating a mean value of all normalized quality difference values and the normalized intensity variation difference value of the kth other electromagnetic signal to obtain a signal deviation degree of the kth other electromagnetic signal.

[0030] In an embodiment, the signal deviation degree calculation formula of the kth other electromagnetic signal is:

[0031]

[0032] wherein, represents the signal deviation degree of the kth other electromagnetic signal, represents the intensity variation stability index of the reference electromagnetic signal, represents the intensity variation stability index of the kth other electromagnetic signal, represents the signal-to-noise ratio of the reference electromagnetic signal, represents the signal-to-noise ratio of the kth other electromagnetic signal, represents the bit error rate of the reference electromagnetic signal, represents the bit error rate of the kth other electromagnetic signal, represents the frame synchronization time of the reference electromagnetic signal, represents the frame synchronization time of the kth other electromagnetic signal, represents a linear normalization function.

[0033] It should be noted that the greater the difference between the quality parameter values of each quality parameter of the kth other electromagnetic signal and the reference electromagnetic signal, and the greater the difference between the intensity variation stability indexes, the greater the degree of environmental interference on the kth other electromagnetic signal.

[0034] Since the reference electromagnetic signal is the electromagnetic signal with the least environmental interference during the operation of the industrial Internet of Things device, it can be considered that the environmental interference during the operation period of the reference electromagnetic signal is almost 0, but there may be errors, so the preset error value is set to 0.01, which is not limited here, and the implementer can set it according to the specific scene, that is, 0.01 is taken as the environmental interference intensity in the running environment during the operation period of the reference electromagnetic signal, and the sum between the signal deviation degree of the kth other electromagnetic signal and 0.01 is calculated to obtain the environmental interference intensity in the running environment during the operation period of the kth other electromagnetic signal, denoted as , that is, .

[0035] Similarly, the environmental interference intensity in the running environment during the operation period of each other electromagnetic signal is obtained. At this point, the environmental interference intensity of the electromagnetic signal in the running environment of the industrial Internet of Things device in each operation period is obtained, so as to adaptively set the threshold interval according to the interference intensity of the electromagnetic signal in different running environments, and to identify whether the electromagnetic safety event of the industrial Internet of Things device occurs in the current operation period according to the adaptively set threshold interval, thereby improving the accuracy of identifying the electromagnetic safety event.

[0036] In step S102, any signal parameter for identifying an electromagnetic safety event is obtained, and the initial threshold interval of the any signal parameter of the industrial Internet of Things device in the current operation period is obtained according to the signal parameter value of the any signal parameter in each operation period, and the running state and environmental interference intensity of the industrial Internet of Things device in each operation period.

[0037] The electromagnetic safety event is usually identified by detecting the signal parameter of the electromagnetic signal, for example, the carrier frequency (such as radio frequency, microwave, low frequency, etc.), the abnormal frequency band may indicate interference or malicious signal (such as GPS interference frequency band 1575 MHz); signal bandwidth, sudden wideband anomaly may be interference (such as DDoS type blocking); signal power, super high power may indicate EMP attack; power density, super high value may be high-power emission device interference; signal-to-noise ratio, sudden drop of signal-to-noise ratio may indicate strong interference intervention, etc. In the embodiment of the present application, the power density in each signal parameter of the electromagnetic signal is taken as an example, and whether the electromagnetic safety event of the industrial Internet of Things device occurs in the current period is identified according to the power density.

[0038] The power density value of the electromagnetic signal in each running period is obtained by measuring the power density of the electromagnetic signal of the industrial Internet of Things device in each running period through the power meter. Since the target electromagnetic signal obtained in step S101 is an electromagnetic signal less affected by environmental interference, and the non-target electromagnetic signal is an electromagnetic signal more affected by environmental interference, when the intensity of environmental interference increases, the interference signal will be superimposed on the electromagnetic signal, causing the power density value of the electromagnetic signal to increase, and the threshold value of the power density is in a positive relationship with the intensity of environmental interference. Therefore, in the embodiment of the present application, according to the power density values of all target electromagnetic signals, the basic threshold interval of the power density is obtained by using the 3sigma principle, and the average value of the intensity of environmental interference in the running environment of all target electromagnetic signals in the running period is calculated as the overall environmental interference intensity of the basic threshold interval, so that the first threshold interval of the power density of the industrial Internet of Things device in the current period based on the intensity of environmental interference is obtained according to the difference between the intensity of environmental interference in the running period of each non-target electromagnetic signal and the overall environmental interference intensity of the basic threshold interval, and the basic threshold interval of the power density is adjusted according to the first threshold interval, to improve the accuracy of identifying electromagnetic safety events, wherein the 3sigma principle is a prior art and will not be described here.

[0039] Then the step of obtaining the first threshold interval is:

[0040] (1) At least one reference threshold interval of the power density is obtained according to the similarity of the intensity of environmental interference corresponding to each non-target electromagnetic signal, and the overall environmental interference intensity of each reference threshold interval.

[0041] Specifically, the intensity of environmental interference in the running environment of all non-target electromagnetic signals in the running period is recorded as the environmental interference to be analyzed, and the environmental interference to be analyzed interval is obtained according to all environmental interference to be analyzed, and the environmental interference to be analyzed interval is divided into 5 subintervals, i.e. the preset number is set to 5, which is not limited here, and the implementer can set the number of subintervals according to the specific scene, for example, assuming that each environmental interference to be analyzed is (0.20, 0.10, 0.25, 0.30, 0.40, 0.33, 0.36, 0.40, 0.10, 0.60), the environmental interference to be analyzed interval is [0.10, 0.60], and the environmental interference to be analyzed interval is divided into 5 subintervals, each subinterval is [0.10, 0.20), [0.20, 0.30), [0.30, 0.40), [0.40, 0.50), [0.50, 0.60];

[0042] For any sub-interval, at least two non-target electromagnetic signals corresponding to the to-be-analyzed environmental interference intensity belonging to the any sub-interval are obtained, which are recorded as environment similar electromagnetic signals, and a maximum value and a minimum value in power density values of all environment similar electromagnetic signals are used to form a reference threshold interval of the power density corresponding to the any sub-interval. Taking the sub-interval [0.30, 0.40) as an example, the to-be-analyzed environmental interference intensities belonging to the sub-interval [0.30, 0.40) are 0.30, 0.33 and 0.36, the non-target electromagnetic signals with the to-be-analyzed environmental interference intensities of 0.30, 0.33 and 0.36 are recorded as environment similar electromagnetic signals, and assuming that the power density values of the environment similar electromagnetic signals are 0.20, 0.22 and 0.31 respectively, the reference threshold interval of the power density corresponding to the sub-interval [0.30, 0.40) is [0.20, 0.31].

[0043] Similarly, the reference threshold interval of the power density corresponding to each sub-interval is obtained.

[0044] Further, the overall environmental interference intensity of each reference threshold interval is obtained, and specifically:

[0045] For any reference threshold interval, a non-target electromagnetic signal corresponding to a signal parameter value of the any signal parameter belonging to the any reference threshold interval is obtained, which is recorded as a to-be-analyzed electromagnetic signal, an average value of environmental interference intensities corresponding to all to-be-analyzed electromagnetic signals is calculated, and the average value is used as the overall environmental interference intensity of the any reference threshold interval.

[0046] Similarly, the overall environmental interference intensity of each reference threshold interval is obtained.

[0047] At this point, at least one reference threshold interval of the power density and the overall environmental interference intensity of each reference threshold interval are obtained.

[0048] (2) The current environmental interference intensity of the industrial Internet of Things device in the current running period is obtained, a first threshold interval of the power density corresponding to the current environmental interference intensity is obtained according to a fitting relationship between each reference threshold interval of the power density and the overall environmental interference intensity thereof, and the current environmental interference intensity.

[0049] Specifically, at least one environment index for representing the running environment of the industrial Internet of Things device in each running period is obtained, such as temperature, humidity, air pressure, etc. The environment data of each environment index in each running period and the environment interference intensity are used to train an environment interference intensity acquisition model to obtain a trained environment interference intensity acquisition model. The current environment interference intensity of the industrial Internet of Things device in the current running period is obtained according to the trained environment interference intensity acquisition model and the environment data of each environment index in the current running period. The environment interference intensity acquisition model belongs to an LSTM model, and the training of the LSTM model is a prior art and will not be described here.

[0050] The overall environment interference intensity of each reference threshold interval is obtained. The difference between the overall environment interference intensity of each reference threshold interval and the overall environment interference intensity of the basic threshold interval is calculated to obtain the environment intensity change value corresponding to each reference threshold interval. The difference between the minimum value of each reference threshold interval and the minimum value of the basic threshold interval is calculated to obtain the left offset corresponding to each reference threshold interval.

[0051] All left offsets and all environment intensity change values are mapped to a two-dimensional coordinate system, where the horizontal coordinate represents the environment intensity change value and the vertical coordinate represents the left offset. The least squares method is used to perform polynomial fitting on the data in the two-dimensional coordinate system to obtain a left offset relationship curve between the environment intensity change value and the left offset. The least squares method is a prior art and will not be described here.

[0052] The right offset between the maximum value of each reference threshold interval and the maximum value of the basic threshold interval is calculated. The right offset relationship curve is obtained according to all right offsets and all environment intensity change values.

[0053] The difference between the current environment interference intensity and the overall environment interference intensity difference of the basic threshold interval is calculated to obtain the current environment intensity change value. The current left offset and the current right offset of the current environment intensity change value are obtained according to the left offset relationship curve, the right offset relationship curve, and the current environment intensity change value.

[0054] The sum of the minimum value of the basic threshold interval and the current left offset is calculated to obtain the current minimum value. The sum of the maximum value of the basic threshold interval and the current right offset is calculated to obtain the current maximum value. The first threshold interval of the power density corresponding to the current environment interference intensity is composed of the current minimum value and the current maximum value.

[0055] For example, if the basic threshold interval of the power density is [0.10, 0.25], the overall environmental interference intensity of the basic threshold interval is 0.01; each reference threshold interval of the power density is [0.20, 0.31], [0.25, 0.31], and [0.17, 0.33]; the overall environmental interference intensity of the reference threshold interval [0.20, 0.31] is 0.12; the overall environmental interference intensity of the reference threshold interval [0.25, 0.31] is 0.15; and the overall environmental interference intensity of the reference threshold interval [0.17, 0.33] is 0.05.

[0056] The environmental intensity change value corresponding to each reference threshold interval is calculated: the environmental intensity change value corresponding to the reference threshold interval [0.20, 0.31] is 0.12-0.01=0.11; the environmental intensity change value corresponding to the reference threshold interval [0.25, 0.31] is 0.15-0.01=0.14; and the environmental intensity change value corresponding to the reference threshold interval [0.17, 0.33] is 0.05-0.01=0.04.

[0057] The left offset corresponding to each reference threshold interval is calculated: the left offset corresponding to the reference threshold interval [0.20, 0.31] is 0.20-0.10=0.10; the left offset corresponding to the reference threshold interval [0.25, 0.31] is 0.25-0.10=0.15; and the left offset corresponding to the reference threshold interval [0.17, 0.33] is 0.17-0.10=0.07.

[0058] The right offset corresponding to each reference threshold interval is calculated: the left offset corresponding to the reference threshold interval [0.20, 0.31] is 0.31-0.25=0.06; the left offset corresponding to the reference threshold interval [0.25, 0.31] is 0.31-0.25=0.06; and the left offset corresponding to the reference threshold interval [0.17, 0.33] is 0.33-0.25=0.08.

[0059] The polynomial fitting is performed on all the left offsets and all the environmental intensity change values to obtain a left offset relationship curve, the difference between the current environmental interference intensity and the overall environmental interference intensity of the basic threshold interval is substituted into the left offset relationship curve, and the current left offset is obtained, which is assumed to be 0.02. Similarly, the right offset relationship curve is obtained, and the current right offset is obtained, which is assumed to be 0.05.

[0060] The current minimum value is 0.10+0.02=0.12, and the current maximum value is 0.25+0.05=0.30, so the first threshold interval of the power density corresponding to the current environmental interference intensity is [0.12, 0.30].

[0061] Thus, the first threshold interval of the power density of the industrial Internet of Things device based on the environmental interference intensity in the current time period is obtained.

[0062] It is also considered that the industrial Internet of Things device has different states in the running process, such as starting, steady-state running, dynamic load running, mode switching, and shutting down. In the steady-state running state, the electromagnetic signal usually remains a relatively stable change, while in the remaining states, such as starting and shutting down, the power supply circuit generates a transient electromagnetic pulse, which may cause the change amplitude of the electromagnetic signal to become large. Therefore, in addition to the first threshold interval based on the environmental interference for adaptively adjusting the basic threshold interval of the power density, a second threshold interval of the power density of the industrial Internet of Things device based on the running state in the current time period is obtained based on the running state of the industrial Internet of Things device in the current running time period, so as to adaptively adjust the basic threshold interval of the power density in combination with the first threshold interval and the second threshold interval, and improve the accuracy of identifying the electromagnetic safety event.

[0063] The specific way of obtaining the second threshold interval is as follows:

[0064] Any state indicator for representing a change in the running state of the industrial Internet of Things device is obtained, such as device temperature, device vibration frequency, current, voltage, and the like. In the embodiment of the present application, the current is taken as an example. For the xth running time period, the current value (i.e., state data) at each time in the xth running time period is obtained, the reciprocal of the sum of the constant 1 and the standard deviation of all current values is calculated, and a state data change stability indicator in the xth running time period is obtained, denoted as , that is, , wherein represents the standard deviation of all current values, The smaller the value is, the more concentrated the distribution of the current value in the xth running time period is, The larger the value is, the more stable the current change in the xth running time period is.

[0065] Similarly, the state data change stability indicator in each running time period is obtained. According to the state data change stability indicator in the running time period of the corresponding electromagnetic signal in each reference threshold interval and the basic threshold interval of the power density, a second fitting relationship between the state data change stability indicator and the threshold interval of the power density is obtained.

[0066] obtain a state feature value of the industrial internet of things device in the current runtime period by calculating an average value of the state data variation stability indexes in all runtime periods with the same current runtime state, and obtaining the second threshold interval of the power density corresponding to the current runtime state according to the state feature value and the second fitting relationship.

[0067] For example, assuming that the state data variation stability indexes are 0.1, 0.2 and 0.3, the power density value of the electromagnetic signal in the runtime period with the state data variation stability index 0.1 belongs to the basic threshold interval [0.10, 0.25], the power density value of the electromagnetic signal in the runtime period with the state data variation stability index 0.2 belongs to the reference threshold interval [0.20, 0.31], and the power density value of the electromagnetic signal in the runtime period with the state data variation stability index 0.3 belongs to the reference threshold interval [0.25, 0.31]. The minimum value relationship curve is fitted according to the state data variation stability index, the minimum value of the basic threshold interval, and the minimum value of each reference threshold interval by using the least square method, the maximum value relationship curve is fitted according to the state data variation stability index, the maximum value of the basic threshold interval, and the maximum value of each reference threshold interval, the state feature value of the industrial internet of things device in the current runtime period is substituted into the minimum value relationship curve to obtain the minimum value of the second threshold interval, which is assumed to be 0.25, the state feature value of the industrial internet of things device in the current runtime period is substituted into the maximum value relationship curve to obtain the maximum value of the second threshold interval, which is assumed to be 0.33, and thus the second threshold interval is [0.25, 0.33].

[0068] At this point, the second threshold interval of the power density of the industrial internet of things device in the current runtime period based on the runtime state is obtained.

[0069] Further, the basic threshold interval of the power density is adaptively adjusted in combination with the first threshold interval and the second threshold interval to obtain an initial threshold interval of the power density of the industrial internet of things device in the current runtime period, and specifically:

[0070] A ratio between the interval width of the first threshold interval and the interval width of the basic threshold interval is calculated to obtain a first threshold interval change multiple, denoted as A ratio between the interval width of the second threshold interval and the interval width of the basic threshold interval is calculated to obtain a second threshold interval change multiple, denoted as ;

[0071] calculating a sum of the first threshold interval variation multiple and the second threshold interval variation multiple to obtain a total threshold interval variation multiple, denoted as calculating a product of an interval width of the base threshold interval and the total threshold interval variation multiple, and subtracting the interval width of the base threshold interval from the product to obtain a total threshold interval variation amplitude;

[0072] subtracting one-half times the total threshold interval variation amplitude from the minimum value of the base threshold interval to obtain a target difference value, if the target difference value is greater than or equal to zero, taking the target difference value as a minimum value in an initial threshold interval of the power density of the industrial internet of things device in the current running period, calculating a sum between the maximum value of the base threshold interval and one-half times the total threshold interval variation amplitude to obtain the target difference value as a maximum value of the power density of the industrial internet of things device in the current running period;

[0073] if the target difference value is less than zero, taking the constant 0 as a minimum value of the power density of the industrial internet of things device in the current running period, calculating a difference between the total threshold interval variation amplitude and the minimum value of the base threshold interval, and taking a sum between the difference and the maximum value of the base threshold interval as a maximum value of the power density of the industrial internet of things device in the current running period;

[0074] composing an initial threshold interval of the power density of the industrial internet of things device in the current running period according to the minimum value and the maximum value of the power density of the industrial internet of things device in the current running period.

[0075] For example, assuming that the base threshold interval is [0.2, 0.4], if the total threshold interval variation amplitude is 0.2, one-half times the total threshold interval variation amplitude is 0.1, the target difference value is 0.2-0.1=0.1, and 0.1 is greater than 0, then the minimum value in the initial threshold interval of the power density of the industrial internet of things device in the current running period is 0.1, the maximum value in the initial threshold interval of the power density of the industrial internet of things device in the current running period is 0.4+0.1=0.5, and the initial threshold interval of the power density of the industrial internet of things device in the current running period is [0.1, 0.5];

[0076] If the total threshold interval variation amplitude is 0.5, the half of the total threshold interval variation amplitude is 0.25, the target difference is 0.2-0.25=-0.05, -0.05 is less than 0, so the minimum value of the initial threshold interval of the power density of the industrial internet of things device in the current running period is 0, the maximum value of the initial threshold interval of the power density of the industrial internet of things device in the current running period is 0.4+0.5-0.2=0.7, that is, the initial threshold interval of the power density of the industrial internet of things device in the current running period is [0, 0.7].

[0077] Up to now, the initial threshold interval of the power density of the industrial internet of things device in the current running period is obtained by adaptively adjusting the basic threshold interval of the power density according to the environmental interference intensity and the running state of the industrial internet of things device.

[0078] Step S103, the initial threshold interval is used to re-identify whether an electromagnetic safety event occurs in the industrial internet of things device in at least two historical periods, and the false positive rate and the false negative rate of the initial threshold interval for identifying the electromagnetic safety event in the historical period are obtained.

[0079] After obtaining the initial threshold interval of the power density of the industrial internet of things device in the current running period through step S102, the accuracy of the initial threshold interval of the power density for identifying the electromagnetic safety event needs to be further detected.

[0080] The power density values of the electromagnetic signals of the industrial internet of things device in at least two historical periods are obtained, at least one historical period in which an electromagnetic safety event occurs is included in all historical periods, the environmental interference intensity in each historical period is the same as that in the current running period, the running state of the industrial internet of things device in each historical period is the same as that in the current running period, the initial threshold interval of the power density of the industrial internet of things device in the current running period is used to re-identify whether an electromagnetic safety event occurs in each historical period, and the false positive rate and the false negative rate corresponding to the initial threshold interval are obtained. The initial threshold interval is corrected according to the false positive rate and the false negative rate, whether an electromagnetic safety event occurs in the industrial internet of things device in the current running period is identified according to the corrected threshold interval, and the accuracy of identifying the electromagnetic safety event is improved.

[0081] Step S104, according to the false positive rate and the false negative rate, the initial threshold interval is corrected to obtain the final threshold interval of any signal parameter of the industrial internet of things device in the current running period, and whether an electromagnetic safety event occurs in the industrial internet of things device in the current running period is identified in real time according to the final threshold interval of each signal parameter of the industrial internet of things device in the current running period.

[0082] After the false alarm rate and the missed alarm rate corresponding to the initial threshold interval are obtained through step S103, the initial threshold interval is corrected according to the false alarm rate and the missed alarm rate, and the final threshold interval of the power density is obtained, specifically:

[0083] The power density values of the electromagnetic signals in each historical period are obtained respectively to obtain a signal parameter value sequence, the absolute value of the difference between each two data in the signal parameter value sequence is calculated to obtain a paired absolute difference sequence, and the minimum value in the paired absolute difference sequence is taken as an adjustment amplitude for adjusting the initial threshold interval, for example: the signal parameter value sequence is (0.5, 0.6, 0.4, 0.2), and the paired absolute difference sequence is (0.1, 0.1, 0.3, 0.2, 0.4, 0.2), wherein the minimum value is 0.1, that is, the adjustment amplitude is 0.1;

[0084] If the missed alarm rate is equal to the false alarm rate, the initial threshold interval is taken as the final threshold interval of the power density of the industrial Internet of Things device in the current running period;

[0085] If the missed alarm rate is greater than the false alarm rate, it indicates that the initial threshold interval is too large, causing part of the electromagnetic signals that occur electromagnetic safety events to be missed, at this time, the initial threshold interval needs to be reduced, the sum between the minimum value in the initial threshold interval and the adjustment amplitude is calculated to obtain a new minimum value, the difference between the maximum value in the initial threshold interval and the adjustment amplitude is calculated to obtain a new maximum value, and the new threshold interval of the power density of the industrial Internet of Things device in the current running period is composed according to the new minimum value and the new maximum value, for example: assuming that the initial threshold interval is [0.10, 0.40] and the adjustment amplitude is 0.05, when the missed alarm rate is greater than the false alarm rate, the new threshold interval is [0.15, 0.35];

[0086] If the missed alarm rate is less than the false alarm rate, it indicates that the initial threshold interval is too small, causing part of the electromagnetic signals that do not occur electromagnetic safety events to be falsely reported, at this time, the initial threshold interval needs to be expanded, the difference between the minimum value in the initial threshold interval and the adjustment amplitude is calculated to obtain a new minimum value, the sum between the maximum value in the initial threshold interval and the adjustment amplitude is calculated to obtain a new maximum value, and the new threshold interval of the power density of the industrial Internet of Things device in the current running period is composed according to the new minimum value and the new maximum value, for example: assuming that the initial threshold interval is [0.10, 0.40] and the adjustment amplitude is 0.05, when the missed alarm rate is less than the false alarm rate, the new threshold interval is [0.05, 0.45];

[0087] ​With the new threshold interval, it is determined whether an electromagnetic safety event of the industrial Internet of Things device occurs in each of the historical time periods, and a new false alarm rate and a new missing alarm rate of the new threshold interval for identifying the electromagnetic safety event in the historical time periods are obtained;

[0088] According to the new false alarm rate and the new missing alarm rate, the new threshold interval is corrected according to the process of correcting the initial threshold interval, and a corrected new threshold interval is obtained. The corrected new threshold interval is used as the new threshold interval, and the method of obtaining the new false alarm rate and the new missing alarm rate is repeated. In this way, until the new false alarm rate and the new missing alarm rate meet a preset condition, the new threshold interval corresponding to the preset condition is used as the final threshold interval of the power density of the industrial Internet of Things device in the current running time period. The preset condition is that the false alarm rate or the missing alarm rate no longer decreases, or both are the same, that is, the new false alarm rate corresponding to the corrected new threshold interval is equal to the new false alarm rate corresponding to the last corrected new threshold interval, or the new missing alarm rate corresponding to the corrected new threshold interval is equal to the new missing alarm rate corresponding to the last corrected new threshold interval, or the new false alarm rate and the new missing alarm rate corresponding to the corrected new threshold interval are equal.

[0089] After obtaining the final threshold interval of the power density of the industrial Internet of Things device in the current running time period, the final threshold interval of each signal parameter (such as carrier frequency, bandwidth, power, signal-to-noise ratio, etc.) of the industrial Internet of Things device in the current running time period is obtained in the same way. If the signal parameter value of at least one signal parameter is not in the final threshold interval, it is determined that an electromagnetic safety event of the industrial Internet of Things device occurs in the current running time period.

[0090] The above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalent ones. These modifications or replacements do not change the essence of the corresponding technical solutions, and should be included in the protection scope of the present application.

Claims

1. An industrial Internet of Things electromagnetic safety event rapid identification and processing method, characterized in that, The industrial Internet of Things electromagnetic safety event rapid identification and processing method comprises the following steps: An industrial Internet of Things device is obtained at least two running time periods before the current running time period without electromagnetic safety events, and the environmental interference intensity in the running environment of each running time period is obtained according to the quality of the electromagnetic signal in each running time period and the running environment of the industrial Internet of Things device in each running time period. Any signal parameter for identifying electromagnetic safety events is obtained, and the initial threshold interval of the any signal parameter of the industrial Internet of Things device in the current running time period is obtained according to the signal parameter value of the any signal parameter in each running time period, the running state and the environmental interference intensity of the industrial Internet of Things device in each running time period. The initial threshold interval is used to re-identify whether the electromagnetic safety event of the industrial Internet of Things device in at least two historical time periods occurs, and the false positive rate and the false negative rate of the initial threshold interval for identifying the electromagnetic safety event in the historical time period are obtained. The initial threshold interval is corrected according to the false positive rate and the false negative rate, and the final threshold interval of the any signal parameter of the industrial Internet of Things device in the current running time period is obtained, and the electromagnetic safety event of the industrial Internet of Things device in the current running time period is identified in real time according to the final threshold interval of each signal parameter of the industrial Internet of Things device in the current running time period.

2. The method according to claim 1, characterized in that, The environmental interference intensity in the running environment of each running time period is obtained according to the quality of the electromagnetic signal in each running time period and the running environment of the industrial Internet of Things device in each running time period, which comprises the following steps: At least one quality parameter for judging the quality of the electromagnetic signal and a preset threshold interval of each quality parameter are obtained, and the quality parameter comprises the signal-to-noise ratio, the bit error rate and the frame synchronization time. The quality parameter value of each quality parameter of the electromagnetic signal in any running time period is obtained, and if the quality parameter value of each quality parameter is in the preset threshold interval, the electromagnetic signal in the any running time period is recorded as a target electromagnetic signal. All target electromagnetic signals are obtained, the intensity variation stability index of each target electromagnetic signal is obtained according to the electromagnetic signal intensity of each target electromagnetic signal, the target electromagnetic signal corresponding to the maximum value in all intensity variation stability indexes is selected as a reference electromagnetic signal with the minimum environmental interference in the running process of the industrial Internet of Things device. The electromagnetic signal in each running time period except the running time period of the reference electromagnetic signal is recorded as another electromagnetic signal, and the environmental interference intensity in the running environment of each running time period is obtained according to the signal quality difference and the intensity variation difference between each other electromagnetic signal and the reference electromagnetic signal.

3. The method of claim 2, wherein, The intensity variation stability index of each target electromagnetic signal is obtained according to the electromagnetic signal intensity of each target electromagnetic signal. Obtaining a target intensity parameter for measuring the intensity of an electromagnetic signal, for any target electromagnetic signal, obtaining the intensity value of the target intensity parameter at each time within the operation period in which the target electromagnetic signal is located, calculating the reciprocal of the sum of the constant 1 and the standard deviation of all intensity values, obtaining the intensity variation stability index of the target electromagnetic signal.

4. The method of claim 2, wherein the method further comprises: The environmental interference intensity in the running environment of each operation period is obtained according to the signal quality difference and the intensity variation difference between each of the other electromagnetic signals and the reference electromagnetic signal, which comprises: For any other electromagnetic signal, the quality difference value between the quality parameter value of each quality parameter of the any other electromagnetic signal and the reference electromagnetic signal, and the intensity variation difference value between the intensity variation stability index of the any other electromagnetic signal and the reference electromagnetic signal are calculated respectively, and each of the quality difference value and the intensity variation difference value is linearly normalized to obtain the normalized quality difference value of each of the quality difference value and the normalized intensity variation difference value of the intensity variation difference value; The mean value of all normalized quality difference values and the normalized intensity variation difference value of the any other electromagnetic signal is calculated to obtain the signal deviation degree of the any other electromagnetic signal; A preset error value is taken as the environmental interference intensity in the running environment of the operation period in which the reference electromagnetic signal is located, and the sum between the signal deviation degree of the any other electromagnetic signal and the preset error value is calculated to obtain the environmental interference intensity in the running environment of the operation period in which the any other electromagnetic signal is located.

5. The method of claim 2, wherein the method further comprises: The initial threshold interval of the any signal parameter of the industrial internet of things device in the current operation period is obtained according to the signal parameter value of the any signal parameter in each operation period, and the running state and the environmental interference intensity of the industrial internet of things device in each operation period, which comprises: The signal parameter value of the any signal parameter of the electromagnetic signal in each operation period is obtained respectively, and the 3sigma principle is used to obtain the basic threshold interval of the any signal parameter according to the signal parameter value of all target electromagnetic signals, and the average value of the environmental interference intensity in the running environment of each operation period in which the target electromagnetic signal is located is calculated to obtain the overall environmental interference intensity of the basic threshold interval; At least one reference threshold interval of the any signal parameter is obtained according to the similarity of the environmental interference intensity corresponding to each non-target electromagnetic signal, and for any reference threshold interval, the non-target electromagnetic signal corresponding to the signal parameter value of the any signal parameter belonging to the any reference threshold interval is obtained, which is recorded as an electromagnetic signal to be analyzed, and the average value of the environmental interference intensity corresponding to all electromagnetic signals to be analyzed is calculated to obtain the overall environmental interference intensity of the any reference threshold interval. The environment indicators are obtained, the environment interference intensity acquisition model is trained by using the environment data of each environment indicator and the environment interference intensity in each running period, a trained environment interference intensity acquisition model is obtained, the current environment interference intensity of the industrial internet of things equipment in the current running period is obtained according to the trained environment interference intensity acquisition model and the environment data of each environment indicator of the industrial internet of things equipment in the current running period, and the current environment interference intensity of the industrial internet of things equipment in the current running period is obtained. The overall environment interference intensity of each reference threshold interval is obtained, the first fitting relationship between each reference threshold interval and the overall environment interference intensity of each reference threshold interval is obtained, and the first threshold interval of the any signal parameter corresponding to the current environment interference intensity is obtained according to the first fitting relationship and the current environment interference intensity. Any state indicator for representing a change in the running state of the industrial internet of things equipment is obtained, the state data of the any state indicator at each time in any running period is obtained, the reciprocal of the sum of the constant 1 and the standard deviation of all state data is calculated to obtain the state data change stability indicator in the any running period, and the second fitting relationship between the threshold interval of the any signal parameter and the state data change stability indicator is obtained according to the reference threshold interval of the any signal parameter and the state data change stability indicator of the corresponding electromagnetic signal in the running period of the basic threshold interval. The current running state of the industrial internet of things equipment in the current running period is obtained, the average value of the state data change stability indicators in all running periods with the same current running state is calculated to obtain the state feature value of the industrial internet of things equipment in the current running period, and the second threshold interval of the any signal parameter corresponding to the current running state is obtained according to the state feature value and the second fitting relationship. The basic threshold interval is adjusted according to the first threshold interval and the second threshold interval to obtain the initial threshold interval of the any signal parameter of the industrial internet of things equipment in the current running period.

6. The method of claim 5, wherein the method further comprises: The at least one reference threshold interval of the any signal parameter is obtained according to the similarity of the environment interference intensity corresponding to each non-target electromagnetic signal, including: The environment interference intensity of the running environment in the running period of all non-target electromagnetic signals is recorded as the analyzed environment interference intensity, the analyzed environment interference intensity interval is obtained according to all analyzed environment interference intensities, and the analyzed environment interference intensity interval is divided into a preset number of subintervals. For any subinterval, at least two non-target electromagnetic signals corresponding to the analyzed environment interference intensity belonging to the any subinterval are obtained and recorded as environment similar electromagnetic signals, and the reference threshold interval of the any signal parameter corresponding to the any subinterval is composed of the maximum value and the minimum value of the signal parameter value of all environment similar electromagnetic signals.

7. The method of claim 5, wherein the method further comprises: The first fitting relationship between each of the reference threshold intervals and the overall ambient interference intensity of each of the reference threshold intervals, and the current ambient interference intensity, obtain the first threshold interval of the any signal parameter corresponding to the current ambient interference intensity, comprising: Respectively calculate the difference value of the overall ambient interference intensity difference between each of the reference threshold intervals and the basic threshold interval, obtain the environmental intensity change value corresponding to each of the reference threshold intervals, and respectively calculate the difference value between the minimum value of each of the reference threshold intervals and the minimum value of the basic threshold interval, obtain the left offset corresponding to each of the reference threshold intervals; Map all left offsets and all environmental intensity change values to a two-dimensional coordinate system, the horizontal coordinate of the two-dimensional coordinate system represents the environmental intensity change value, and the vertical coordinate represents the left offset, and polynomial fitting is performed on the data in the two-dimensional coordinate system to obtain a left offset relationship curve between the environmental intensity change value and the left offset; Respectively calculate the right offset between the maximum value of each of the reference threshold intervals and the maximum value of the basic threshold interval, and obtain a right offset relationship curve according to all right offsets and all environmental intensity change values; Calculate the difference value between the current ambient interference intensity and the overall ambient interference intensity difference of the basic threshold interval, obtain the current environmental intensity change value, and obtain the current left offset and the current right offset of the current environmental intensity change value according to the left offset relationship curve, the right offset relationship curve, and the current environmental intensity change value; Calculate the sum of the minimum value of the basic threshold interval and the current left offset to obtain the current minimum value, calculate the sum of the maximum value of the basic threshold interval and the current right offset to obtain the current maximum value, and according to the current minimum value and the current maximum value, the first threshold interval of the any signal parameter corresponding to the current ambient interference intensity is composed.

8. The method of claim 5, wherein the method further comprises: The first threshold interval and the second threshold interval are used to adjust the basic threshold interval to obtain the initial threshold interval of the any signal parameter of the industrial internet of things device in the current running period, comprising: Calculate the ratio between the interval width of the first threshold interval and the interval width of the basic threshold interval to obtain the first threshold interval change multiple, calculate the ratio between the interval width of the second threshold interval and the interval width of the basic threshold interval to obtain the second threshold interval change multiple; Calculate the sum of the first threshold interval change multiple and the second threshold interval change multiple to obtain the total threshold interval change multiple, calculate the product between the interval width of the basic threshold interval and the total threshold interval change multiple, subtract the interval width of the basic threshold interval from the product to obtain the total threshold interval change amplitude; subtracting one-half times the total threshold interval variation range from the minimum value of the basic threshold interval, obtaining a target difference value, if the target difference value is greater than or equal to zero, taking the target difference value as the minimum value of the initial threshold interval of the any signal parameter of the industrial internet of things device in the current running period, calculating the sum between the maximum value of the basic threshold interval and one-half times the total threshold interval variation range, obtaining the target difference value as the maximum value of the any signal parameter of the industrial internet of things device in the current running period; if the target difference value is less than zero, taking the constant 0 as the minimum value of the any signal parameter of the industrial internet of things device in the current running period, calculating the difference between the total threshold interval variation range and the minimum value of the basic threshold interval, taking the sum between the difference and the maximum value of the basic threshold interval as the maximum value of the any signal parameter of the industrial internet of things device in the current running period; composing the initial threshold interval of the any signal parameter of the industrial internet of things device in the current running period according to the minimum value and the maximum value of the any signal parameter of the industrial internet of things device in the current running period.

9. The method of claim 1, wherein the method further comprises: The method for correcting the initial threshold interval according to the false alarm rate and the missed alarm rate to obtain the final threshold interval of the any signal parameter of the industrial internet of things device in the current running period comprises: obtaining the signal parameter value sequence by obtaining the signal parameter value of the any signal parameter of the electromagnetic signal in each historical period respectively, obtaining the pair absolute difference sequence by calculating the absolute value of the difference between each two data in the signal parameter value sequence, taking the minimum value in the pair absolute difference sequence as the adjustment range for adjusting the initial threshold interval; if the missed alarm rate is equal to the false alarm rate, taking the initial threshold interval as the final threshold interval of the any signal parameter of the industrial internet of things device in the current running period; if the missed alarm rate is greater than the false alarm rate, calculating the sum between the minimum value in the initial threshold interval and the adjustment range, obtaining a new minimum value, calculating the difference between the maximum value in the initial threshold interval and the adjustment range, obtaining a new maximum value, and composing a new threshold interval of the any signal parameter of the industrial internet of things device in the current running period according to the new minimum value and the new maximum value; if the missed alarm rate is less than the false alarm rate, calculating the difference between the minimum value in the initial threshold interval and the adjustment range, obtaining a new minimum value, calculating the sum between the maximum value in the initial threshold interval and the adjustment range, obtaining a new maximum value, and composing a new threshold interval of the any signal parameter of the industrial internet of things device in the current running period according to the new minimum value and the new maximum value; re-identifying whether the electromagnetic safety event occurs in each of the historical periods by using the new threshold interval, obtaining a new false alarm rate and a new missed alarm rate of the new threshold interval for identifying the electromagnetic safety event in the historical periods; According to the new false alarm rate and the new missed alarm rate, the new threshold interval is corrected to obtain a corrected new threshold interval, the corrected new threshold interval is taken as the new threshold interval, the method of obtaining the new false alarm rate and the new missed alarm rate is repeated until the new false alarm rate and the new missed alarm rate meet a preset condition, a new threshold interval corresponding to the preset condition is taken as a final threshold interval of the any signal parameter of the industrial Internet of Things device in the current operation period, and the preset condition includes that a new false alarm rate corresponding to the corrected new threshold interval is equal to a new false alarm rate corresponding to a last round of corrected new threshold interval, or a new missed alarm rate corresponding to the corrected new threshold interval is equal to a new missed alarm rate corresponding to the last round of corrected new threshold interval, or the new false alarm rate and the new missed alarm rate corresponding to the corrected new threshold interval are equal.

10. The method of claim 1, wherein, The real-time identification of whether an electromagnetic safety event of the industrial Internet of Things device occurs in the current operation period according to the final threshold interval of each signal parameter of the industrial Internet of Things device in the current operation period includes: The signal parameter value and the final threshold interval of each signal parameter of the industrial Internet of Things device in the current operation period are obtained, and if the signal parameter value of at least one signal parameter is not in the final threshold interval, it is determined that an electromagnetic safety event of the industrial Internet of Things device occurs in the current operation period.

Images