A highway tunnel electromechanical system operation state monitoring and early warning system

Abstract

This invention relates to the field of data anomaly detection, and more particularly to a monitoring and early warning system for the operating status of electromechanical systems in highway tunnels. The system includes a processor and a memory. The processor executes a computer program in the memory to perform the following steps: acquiring a fan speed data sequence and a multi-dimensional feature data sequence; obtaining an initial threshold interval based on the data fluctuation characteristics in the fan speed data sequence; constructing fan speed data subsequences and multi-dimensional feature data subsequences respectively in the fan speed data sequence and the multi-dimensional feature data sequence, obtaining the degree of fan speed deviation at the current sampling time, and optimizing the initial threshold interval to obtain an optimized threshold interval; if the fan speed at the current sampling time is within the optimized threshold interval, then monitoring and early warning are performed based on the differences in oxygen concentration data at different locations within the highway tunnel. This invention provides comprehensive monitoring of the fans, thereby providing accurate early warnings of the fans' operating status.

Description

Technical Field

[0001] This invention relates to the field of data anomaly detection, and in particular to a monitoring and early warning system for the operating status of electromechanical systems in highway tunnels. Background Technology

[0002] With the rapid development of the global economy and transportation industry, highways have become an important link connecting cities and rural areas and promoting regional economic integration. As an important component of highways, tunnels not only greatly shorten travel distances but also improve traffic efficiency. However, the operating status of the electromechanical systems and fans within tunnels directly affects the effectiveness of the ventilation system, and consequently, the air quality and driving safety within the tunnel. As the core component of the ventilation system, the proper operation of the fans is crucial to ensuring air circulation, sufficient oxygen, and the timely removal of harmful gases such as smoke from the tunnel.

[0003] As a core electromechanical device, the operation status of the fan needs to be abnormally detected to ensure the effectiveness of the ventilation system in the tunnel. Due to the influence of factors such as changes in weather conditions, traffic flow fluctuations and equipment aging in the tunnel, the fan speed data often exhibits nonlinear fluctuations. Therefore, the coupling of multiple factors makes the abnormal detection of fan speed more complex.

[0004] Traditional methods use static parameter setting, which sets a fixed threshold range for fan speed in three levels: low, medium, and high. If the fan speed does not match the threshold range for its corresponding level, it is considered that the fan has malfunctioned. However, this method is difficult to adapt to complex and dynamic operating environments. It may overlook potential faults caused by long-term accumulation, and it is also prone to false alarms triggered by short-term fluctuations.

[0005] Therefore, how to comprehensively monitor wind turbines and provide accurate early warnings of their operating status has become an urgent problem to be solved. Summary of the Invention

[0006] In view of this, embodiments of the present invention provide a monitoring and early warning system for the operation status of electromechanical systems in highway tunnels, in order to solve the problem of how to comprehensively monitor the fans and thus provide accurate early warning of the operation status of the fans.

[0007] This invention provides a monitoring and early warning system for the operating status of an electromechanical system in a highway tunnel, comprising a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the following method: The wind turbine speed data and multidimensional feature data related to the wind turbine speed are obtained from each historical sampling moment within a preset time range including the current sampling moment in the highway tunnel. An initial wind turbine speed data sequence and an initial multidimensional feature data sequence are obtained. The initial wind turbine speed data sequence and the initial multidimensional feature data sequence are preprocessed to obtain the wind turbine speed data sequence and the multidimensional feature data sequence, respectively. Based on the data fluctuation characteristics in the wind turbine speed data sequence, the initial threshold range of the wind turbine speed at the current sampling time is obtained; Construct a subsequence of wind turbine speed data and a subsequence of multidimensional feature data including the wind turbine speed data at the current sampling time in the wind turbine speed data sequence and the multidimensional feature data sequence respectively. Obtain the degree of wind turbine speed deviation at the current sampling time based on the correlation between the wind turbine speed data subsequence and the multidimensional feature data subsequence. Optimize and adjust the initial threshold interval based on the degree of wind turbine speed deviation to obtain an optimized threshold interval. If the fan speed at the current sampling time is within the optimized threshold range, then oxygen concentration data at different locations within the highway tunnel are acquired, and the fan speed at the current sampling time is monitored and warned based on the differences in oxygen concentration data at different locations within the highway tunnel.

[0008] Preferably, after optimizing the initial threshold range based on the degree of deviation of the fan speed to obtain the optimized threshold range, the method further includes: If the wind turbine speed at the current sampling time is not within the optimized threshold range, the wind turbine speed data at the current sampling time is determined to be abnormal data. The wind turbine speed data within a future preset time period, including the current sampling time, is continuously monitored. When at least a preset number of wind turbine speed data are abnormal data within the future preset time period, an early warning is issued for the wind turbine speed within the future preset time period. If there are no at least a preset number of abnormal fan speed data within the preset future time period, the fan speed within the preset future time period is determined to be normal.

[0009] Preferably, obtaining the initial threshold range of the wind turbine speed at the current sampling time based on the data fluctuation characteristics in the wind turbine speed data sequence includes: The average value and standard deviation of the wind turbine speed data sequence are obtained. The first difference between the average value and the standard deviation of the first preset multiple is calculated. The first sum of the average value and the standard deviation of the first preset multiple is calculated. The first sum is used as the upper limit and the first difference is used as the lower limit to construct the initial threshold range of the wind turbine speed at the current sampling time.

[0010] Preferably, obtaining the degree of wind turbine speed deviation at the current sampling time based on the correlation between the wind turbine speed data subsequence and the multidimensional feature data subsequence includes: The multidimensional feature data subsequence is split into multiple one-dimensional feature data subsequences according to the dimension. The Pearson correlation coefficient of the wind turbine speed data subsequence and each one-dimensional feature data subsequence is obtained. Based on the proportion of the Pearson correlation coefficient of each one-dimensional feature data subsequence in all Pearson correlation coefficients, the association weight of each one-dimensional feature data subsequence is obtained. Based on the association weight of each one-dimensional feature data subsequence in the multi-dimensional feature data subsequence, and the data fluctuation characteristics in the wind turbine speed data subsequence and the multi-dimensional feature data subsequence, the degree of wind turbine speed deviation at the current sampling time is obtained.

[0011] Preferably, the step of obtaining the degree of wind turbine speed deviation at the current sampling time based on the association weight of each one-dimensional feature data subsequence in the multi-dimensional feature data subsequence, and the data fluctuation characteristics in the wind turbine speed data subsequence and the multi-dimensional feature data subsequence, includes: Any historical sampling time within the time range corresponding to the wind turbine speed data subsequence is recorded as the target sampling time. Based on the difference between the wind turbine speed data at the target sampling time and the average value of the wind turbine speed data subsequence, the deviation of the wind turbine speed data at the target sampling time is obtained. The absolute value of the difference between the wind turbine speed data at the target sampling time and the previous sampling time is obtained. The time interval between the target sampling time and the previous sampling time is obtained. The second ratio of the absolute value of the difference to the time interval is calculated. The second summation result of the second ratio of the constant 1 and the second preset multiple is calculated. The first product of the square of the deviation of the wind turbine speed data at the target sampling time and the second summation result is obtained. Obtain the deviation of feature data for each dimension at the target sampling time. Based on the association weight of each one-dimensional feature data subsequence, perform a weighted summation on the deviation of feature data for each dimension at the target sampling time to obtain a first weighted summation result. Perform a weighted summation on the first product and the first weighted summation result to obtain a second weighted summation result. Obtain the arithmetic square root of the second weighted summation result. Substitute the negative of the arithmetic square root of the second weighted summation result into an exponential function with the natural constant as the base to obtain a first exponential function result. Obtain the second difference between the constant 1 and the first exponential function result to obtain the fan speed deviation value at the target sampling time. Obtain the fan speed deviation values ​​for all historical sampling moments within the time range corresponding to the fan speed data subsequence, and obtain the average value of the fan speed deviation values ​​as the degree of fan speed deviation at the current sampling moment.

[0012] Preferably, the step of optimizing the initial threshold range based on the degree of deviation of the fan speed to obtain an optimized threshold range includes: Obtain the third difference between the first difference and the degree of deviation of the fan speed by the third preset multiple, obtain the third sum of the first sum and the degree of deviation of the fan speed by the third preset multiple, and construct the optimization threshold interval with the third sum as the upper limit and the third difference as the lower limit.

[0013] Preferably, acquiring oxygen concentration data at different locations within the highway tunnel includes: Obtain oxygen concentration data at each historical sampling time within a preset historical period, including the current sampling time, at the two port locations and the middle location of the highway tunnel.

[0014] Preferably, the step of monitoring and issuing early warnings about the fan speed at the current sampling time based on the differences in oxygen concentration data at different locations within the highway tunnel includes: For any historical sampling time within the preset historical period, based on the oxygen concentration data of the two port positions at any historical sampling time, calculate the average oxygen concentration, calculate the absolute value of the oxygen concentration difference between the average oxygen concentration and the oxygen concentration data of the middle position at any historical sampling time, substitute the negative of the absolute value of the oxygen concentration difference into an exponential function with the natural constant as the base, obtain the result of the second exponential function, calculate the difference between the constant 1 and the result of the second exponential function, and obtain the oxygen concentration difference value at any historical sampling time; An oxygen concentration difference threshold is set. When the oxygen concentration difference value of more than half of the historical sampling times within the preset historical period is greater than or equal to the oxygen concentration difference threshold, it is determined that the fan speed at the current sampling time is abnormal, and an early warning is issued for the fan speed at the current sampling time.

[0015] Preferably, the step of monitoring and issuing early warnings about the fan speed at the current sampling time based on the differences in oxygen concentration data at different locations within the highway tunnel further includes: When the oxygen concentration difference value of half or more of the historical sampling times within the preset historical period is less than the oxygen concentration difference threshold, it is determined that the fan speed at the current sampling time is normal, and no warning processing is required for the fan speed at the current sampling time.

[0016] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows: This invention acquires wind turbine speed data and multidimensional feature data related to wind turbine speed at each historical sampling moment within a preset time range, including the current sampling moment, in a highway tunnel, obtaining an initial wind turbine speed data sequence and an initial multidimensional feature data sequence. The initial wind turbine speed data sequence and the initial multidimensional feature data sequence are preprocessed to obtain the wind turbine speed data sequence and the multidimensional feature data sequence, respectively. Based on the data fluctuation characteristics in the wind turbine speed data sequence, an initial threshold range for the wind turbine speed at the current sampling moment is obtained. A packet is constructed in the wind turbine speed data sequence and the multidimensional feature data sequence, respectively. The method includes a subsequence of fan speed data and a subsequence of multidimensional feature data at the current sampling time. Based on the correlation between the subsequence of fan speed data and the subsequence of multidimensional feature data, the deviation of fan speed at the current sampling time is obtained. The initial threshold interval is optimized and adjusted based on the deviation of fan speed to obtain an optimized threshold interval. If the fan speed at the current sampling time is within the optimized threshold interval, oxygen concentration data at different locations in the highway tunnel are obtained. Based on the differences in oxygen concentration data at different locations in the highway tunnel, the fan speed at the current sampling time is monitored and warned. This invention first calculates the deviation of the fan speed at the current sampling moment by using fan speed data at each historical sampling moment within a preset time range and multi-dimensional feature data related to the fan speed, optimizes the initial threshold range, and identifies possible mechanical or electrical faults. Then, by using the differences in oxygen concentration data at different locations in the highway tunnel, it evaluates the ventilation effect of the fan and monitors and warns of the fan speed at the current sampling moment. This not only captures abnormal trends in fan speed but also avoids misjudgments caused by short-term fluctuations in fan speed, ensuring the safe and stable operation of the tunnel, achieving comprehensive monitoring of the fan, and providing accurate early warning of the fan's operating status. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of a method for monitoring and early warning of the operating status of an electromechanical system in a highway tunnel, provided in Embodiment 1 of the present invention. Detailed Implementation

[0019] Embodiments of this disclosure are described in detail below, with examples of these embodiments illustrated in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting it.

[0020] It should be noted that the terms "first," "second," etc., used in this disclosure and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure.

[0021] To illustrate the technical solution of the present invention, specific embodiments are described below.

[0022] This invention provides a monitoring and early warning system for the operational status of an electromechanical system in a highway tunnel, comprising a processor and a memory. The processor executes a computer program in the memory to implement a method for monitoring and early warning the operational status of an electromechanical system in a highway tunnel. Figure 1 As shown, the method includes the following steps: Step S101: Obtain the fan speed data and multidimensional feature data related to the fan speed at each historical sampling time within a preset time range including the current sampling time in the highway tunnel, to obtain an initial fan speed data sequence and an initial multidimensional feature data sequence. Preprocess the initial fan speed data sequence and the initial multidimensional feature data sequence to obtain the fan speed data sequence and the multidimensional feature data sequence, respectively.

[0023] Highway tunnels contain multiple fans, and the method for monitoring and issuing early warnings for the rotational speed of each fan is the same. This embodiment takes the monitoring and early warning method for one of the fans in a highway tunnel as an example for detailed explanation.

[0024] Different types of IoT sensors are installed in the highway tunnel to acquire wind turbine speed data and related multidimensional feature data at a sampling frequency of once per minute. This includes data from each historical sampling moment within the past 8 hours up to the current sampling time. This yields an initial wind turbine speed data sequence and an initial multidimensional feature data sequence. The specific settings are not limited and can be adjusted according to the specific implementation scenario. In this embodiment, wind turbine speed data is collected by a speed sensor mounted on the wind turbine shaft. The multidimensional feature data includes, but is not limited to, current data, voltage data, wind turbine vibration data, temperature data, and humidity data. Current and voltage data are collected by the electrical parameter monitoring module in the motor control system. Wind turbine vibration data is collected by a vibration sensor mounted on the wind turbine casing. Temperature and humidity data are collected by temperature and humidity sensors inside the tunnel. The specific settings are not limited and can be adjusted according to the specific implementation scenario.

[0025] Because traditional highway tunnel ventilation fans have three speed settings (low, medium, and high), different settings can be adjusted according to the tunnel's ventilation needs. For example, the higher the traffic volume and the more pollutants emitted by vehicles, the higher the fan speed may need to be. During periods of low traffic, operating at a lower speed reduces energy consumption and lowers operating costs. Therefore, within the initial 8-hour period for obtaining the initial fan speed sequence, the speed setting may change. If this happens, the initial fan speed data and initial multidimensional feature data sequences are obtained, based on the fan speed setting at the current sampling time. These data include historical sampling times from the previous 8 hours, along with multidimensional feature data related to the fan speed.

[0026] After obtaining the initial wind turbine speed data sequence and the initial multidimensional feature data sequence, in order to eliminate possible problems in the initial wind turbine speed data sequence and the initial multidimensional feature data sequence, it is necessary to perform preprocessing operations on the acquired data to obtain the wind turbine speed data sequence and the multidimensional feature data sequence. The specific preprocessing steps are as follows: For wind turbine speed data, if there is data loss within 10 minutes, linear interpolation is used to fill in the missing values. If the loss time exceeds 10 minutes, it is directly confirmed that the missing wind turbine speed data is caused by manual shutdown or wind turbine abnormality. The data for that period is removed and recorded, without the need for subsequent monitoring and early warning steps. For current and voltage data, which may be affected by instantaneous interference fluctuations, a moving average method is used to smooth the data, preserving the overall trend and removing random noise. For wind turbine vibration data, wavelet transform is used to remove high-frequency noise such as environmental vibration and enhance the key characteristics of wind turbine mechanical vibration. For all data, they are aligned according to the sampling time to ensure that different data at the same sampling time are synchronously associated. Wind turbine speed data, current data, and voltage data are locally standardized, and the data range is standardized to the [0,1] interval to eliminate the influence of different magnitudes or dimensions, making each data point equally important in data analysis. Among these, linear interpolation, moving average, and wavelet transform are existing technologies and will not be elaborated here.

[0027] In one embodiment, to avoid data stacking becoming increasingly large, save computing resources, and improve computing efficiency, a time window can also be set to achieve the same purpose as in this embodiment.

[0028] Step S102: Based on the data fluctuation characteristics in the wind turbine speed data sequence, obtain the initial threshold range of the wind turbine speed at the current sampling time.

[0029] After obtaining the wind turbine speed data sequence and the multidimensional feature data sequence, the initial threshold range of the wind turbine speed at the current sampling time can be obtained based on the data fluctuation characteristics in the wind turbine speed data sequence.

[0030] Specifically, the average value and standard deviation of the wind turbine speed data sequence are obtained, the first difference between the average value and the standard deviation of the first preset multiple is calculated, the first sum of the average value and the standard deviation of the first preset multiple is calculated, and the initial threshold range of the wind turbine speed at the current sampling time is constructed with the first sum as the upper limit and the first difference as the lower limit.

[0031] In one embodiment, the average value of the wind turbine speed data sequence is obtained. and standard deviation Calculate the first difference as The result of the first addition is calculated as follows: Using the first sum as the upper limit and the first difference as the lower limit, an initial threshold range for the fan speed at the current sampling time is constructed. Where k is the first preset multiple, with a reference value of 2. There is no limit here, and it can be set according to the specific implementation scenario.

[0032] Thus, the initial threshold range of the fan speed at the current sampling time is obtained.

[0033] Step S103: Construct a subsequence of wind turbine speed data and a subsequence of multidimensional feature data, including the wind turbine speed data at the current sampling time, in the wind turbine speed data sequence and the multidimensional feature data sequence, respectively. Obtain the degree of wind turbine speed deviation at the current sampling time based on the correlation between the wind turbine speed data subsequence and the multidimensional feature data subsequence. Optimize and adjust the initial threshold interval based on the degree of wind turbine speed deviation to obtain an optimized threshold interval.

[0034] After obtaining the initial threshold range of the wind turbine speed at the current sampling moment, it is important to note that this initial threshold range is set using a static parameter setting method. This method is ill-suited to complex and dynamic operating environments, potentially overlooking long-term accumulated faults and easily triggering false alarms due to short-term fluctuations. Therefore, the initial threshold range needs to be optimized and adjusted to more accurately identify abnormal wind turbine conditions.

[0035] Since current data, voltage data, fan vibration data, temperature data, and humidity data can all affect fan speed, the initial threshold range can be optimized by analyzing the correlation between fan speed data and other feature data. To save computational resources and improve efficiency, this embodiment constructs a fan speed data subsequence and a multidimensional feature data subsequence within one hour of the current sampling time in both the fan speed data sequence and the multidimensional feature data sequence. This is not limited and can be set according to the specific implementation scenario. Based on the correlation between the fan speed data subsequence and the multidimensional feature data subsequence, the degree of fan speed deviation at the current sampling time is obtained. Then, the initial threshold range is optimized by analyzing the degree of fan speed deviation at the current sampling time to obtain an optimized threshold range.

[0036] The method for obtaining the degree of deviation of the wind turbine speed at the current sampling moment based on the correlation between the wind turbine speed data subsequence and the multidimensional feature data subsequence is as follows: (1) The multidimensional feature data subsequence is split into multiple one-dimensional feature data subsequences according to the dimension, and the Pearson correlation coefficient of the wind turbine speed data subsequence and each one-dimensional feature data subsequence is obtained. Based on the proportion of the Pearson correlation coefficient of each one-dimensional feature data subsequence in all Pearson correlation coefficients, the association weight of each one-dimensional feature data subsequence is obtained.

[0037] In one embodiment, the multidimensional feature data subsequence is split into multiple one-dimensional feature data subsequences according to their dimensions, namely, current data subsequence, voltage data subsequence, fan vibration data subsequence, temperature data subsequence, and humidity data subsequence. The Pearson correlation coefficient between the fan speed data subsequence and each one-dimensional feature data subsequence is obtained. The Pearson correlation coefficient is existing technology and will not be elaborated here. Based on the proportion of the Pearson correlation coefficient corresponding to each one-dimensional feature data subsequence among all Pearson correlation coefficients, the association weight of each one-dimensional feature data subsequence is obtained. Taking the i-th one-dimensional feature data subsequence as an example, the formula for calculating the association weight of the i-th one-dimensional feature data subsequence is as follows:

[0038] in, Let be the association weight of the i-th one-dimensional feature data subsequence; denoted as Pearson correlation coefficient between the wind turbine speed data subsequence and the i-th one-dimensional feature data subsequence; i is the index of the one-dimensional feature data subsequence; p is the number of one-dimensional feature data subsequences.

[0039] It should be noted that the larger the Pearson correlation coefficient between the wind turbine speed data subsequence and any one-dimensional feature data subsequence, the greater the correlation between the wind turbine speed data subsequence and any one-dimensional feature data subsequence, and the greater the association weight of the i-th one-dimensional feature data subsequence.

[0040] (2) Based on the association weight of each one-dimensional feature data subsequence in the multidimensional feature data subsequence, and the data fluctuation characteristics in the wind turbine speed data subsequence and the multidimensional feature data subsequence, obtain the degree of wind turbine speed deviation at the current sampling time.

[0041] Specifically, any historical sampling time within the time range corresponding to the wind turbine speed data subsequence is recorded as the target sampling time. Based on the difference between the wind turbine speed data at the target sampling time and the average value of the wind turbine speed data subsequence, the deviation of the wind turbine speed data at the target sampling time is obtained. The absolute value of the difference between the wind turbine speed data at the target sampling time and the previous sampling time is obtained. The time interval between the target sampling time and the previous sampling time is obtained. The second ratio of the absolute value of the difference to the time interval is calculated. The second summation result of the second ratio of the constant 1 and the second preset multiple is calculated. The first product of the square of the deviation of the wind turbine speed data at the target sampling time and the second summation result is obtained. Obtain the deviation of feature data for each dimension at the target sampling time. Based on the association weight of each one-dimensional feature data subsequence, perform a weighted summation on the deviation of feature data for each dimension at the target sampling time to obtain a first weighted summation result. Perform a weighted summation on the first product and the first weighted summation result to obtain a second weighted summation result. Obtain the arithmetic square root of the second weighted summation result. Substitute the negative of the arithmetic square root of the second weighted summation result into an exponential function with the natural constant as the base to obtain a first exponential function result. Obtain the second difference between the constant 1 and the first exponential function result to obtain the fan speed deviation value at the target sampling time. Obtain the fan speed deviation values ​​for all historical sampling moments within the time range corresponding to the fan speed data subsequence, and obtain the average value of the fan speed deviation values ​​as the degree of fan speed deviation at the current sampling moment.

[0042] In one embodiment, any historical sampling time within the time range corresponding to the wind turbine speed data subsequence is recorded as the target sampling time. First, the deviation of the wind turbine speed data at the target sampling time, and the wind turbine speed data at the target sampling time and its previous sampling time are obtained. Then, the deviation of the feature data of each dimension at the target sampling time is obtained. The deviation is a prior art and will not be elaborated here. Finally, based on the association weight of each one-dimensional feature data subsequence, the deviation of the wind turbine speed data at the target sampling time, and the deviation of the feature data of each dimension, the degree of deviation of the wind turbine speed at the current sampling time is calculated.

[0043] Where D represents the degree of deviation of the fan speed at the current sampling moment; The deviation of the fan speed data at the target sampling time; The second preset multiple is 0.1, which is not limited here and can be set according to the specific implementation scenario; S(t) is the fan speed data at the target sampling time; S(t-1) is the fan speed data at the previous sampling time of the target sampling time; The time interval between the target sampling time and its previous sampling time; Let be the deviation of the feature data at the target sampling time in the i-th one-dimensional feature data subsequence; Let p be the association weight of the i-th one-dimensional feature data subsequence; i is the index of the one-dimensional feature data subsequence; p is the number of one-dimensional feature data subsequences. As the first weighting coefficient, This is the second weighting coefficient. and The reference value is 0.5, which is not limited here and can be set according to the specific implementation scenario; e is a natural constant; n is the number of sampling moments within the time range corresponding to the wind turbine speed data subsequence; t is the sequence number of the sampling moments within the time range corresponding to the wind turbine speed data subsequence.

[0044] It should be noted that, This represents the deviation of the fan speed at the target sampling time. The greater the deviation between the fan speed data at the target sampling time and the feature data of each dimension, the greater the deviation of the fan speed at the target sampling time. This indicates a greater likelihood of an abnormal fan speed at the current sampling time, requiring an expansion of the initial threshold range to increase the tolerance for false alarms. Conversely, a smaller deviation indicates that the fan speed at the current sampling time is within a reasonable range, allowing for a more appropriate reduction of the initial threshold range and decreasing the tolerance.

[0045] Furthermore, after obtaining the degree of deviation of the fan speed at the current sampling time, the initial threshold range can be optimized and adjusted based on the degree of deviation of the fan speed at the current sampling time to obtain the optimized threshold range. The specific method is as follows: Obtain the third difference between the first difference and the degree of deviation of the fan speed by the third preset multiple, obtain the third sum of the first sum and the degree of deviation of the fan speed by the third preset multiple, and construct the optimization threshold interval with the third sum as the upper limit and the third difference as the lower limit.

[0046] In one embodiment, the lower limit of the initial threshold range for the fan speed at the current sampling time is denoted as... The upper limit of the initial threshold range for the fan speed at the current sampling time is denoted as... The specific formula for optimizing and adjusting the initial threshold range is as follows:

[0047] in, To optimize the lower threshold within the threshold range; To optimize the upper limit of the threshold within the threshold range; This is the lower limit of the initial threshold range for the fan speed at the current sampling time; The upper limit of the initial threshold range for the fan speed at the current sampling time; The third preset multiple; D is the degree of deviation of the fan speed at the current sampling time.

[0048] It should be noted that, The reference value is determined based on the degree of fan speed deviation at the current sampling time. The threshold for fan speed deviation is set to 0.5, which is not limited here and can be set according to the specific implementation scenario. If the fan speed deviation at the current sampling time is greater than or equal to 0.5, it is confirmed that the fan speed deviation at the current sampling time is high, and the range of the initial threshold interval needs to be expanded. The reference value is taken If the fan speed deviation at the current sampling time is less than 0.5, then the fan speed deviation at the current sampling time is considered small, and the range of the initial threshold interval needs to be narrowed. The reference value is taken ,in, This represents the average value of the subsequence of fan speed data.

[0049] Based on the upper and lower limits of the optimized threshold interval, the optimized threshold interval is constructed as follows: .

[0050] Thus, the optimized threshold range for the current sampling time is obtained.

[0051] Step S104: If the fan speed at the current sampling time is within the optimized threshold range, then obtain the oxygen concentration data at different locations in the highway tunnel, and monitor and warn the fan speed at the current sampling time based on the differences in the oxygen concentration data at different locations in the highway tunnel.

[0052] After obtaining the optimized threshold range for the current sampling time, the fan speed at the current sampling time can be judged based on the optimized threshold range. If the fan speed at the current sampling time is within the optimized threshold range, it indicates that the fan is in working condition at the current sampling time. However, the fact that the fan is in working condition does not necessarily indicate the ventilation effect in the highway tunnel. Therefore, it is necessary to obtain oxygen concentration data at different locations in the highway tunnel, judge the ventilation effect in the highway tunnel based on the oxygen concentration data at different locations in the highway tunnel, and then monitor and warn of the fan speed at the current sampling time based on the differences in oxygen concentration data at different locations in the highway tunnel.

[0053] The step of obtaining oxygen concentration data at different locations within the highway tunnel includes: obtaining oxygen concentration data at each historical sampling time within 5 minutes, including the current sampling time, at the two port locations and the middle location of the highway tunnel. This step is not limited and can be set according to the specific implementation scenario.

[0054] Furthermore, based on the differences in oxygen concentration data at different locations within the highway tunnel, the specific steps for monitoring and issuing early warnings regarding the fan speed at the current sampling time are as follows: (1) For any historical sampling time within the preset historical period, calculate the average oxygen concentration based on the oxygen concentration data of the two port positions at any historical sampling time, calculate the absolute value of the oxygen concentration difference between the average oxygen concentration and the oxygen concentration data of the middle position at any historical sampling time, substitute the negative of the absolute value of the oxygen concentration difference into the exponential function with the natural constant as the base, obtain the result of the second exponential function, calculate the difference between the constant 1 and the result of the second exponential function, and obtain the oxygen concentration difference value at any historical sampling time.

[0055] In one embodiment, taking any historical sampling time as an example, the difference in oxygen concentration at any historical sampling time is calculated:

[0056] in, Let be the difference in oxygen concentration at any historical sampling time; e is the natural constant. Oxygen concentration data at the left end of a highway tunnel at any given historical sampling time; Oxygen concentration data at the right end of a highway tunnel at any historical sampling time; Oxygen concentration data at the middle location of a highway tunnel at any historical sampling time; It is the absolute value symbol.

[0057] It should be noted that the greater the difference between the oxygen concentration data at the two ends and the middle position of the highway tunnel at any historical sampling time, the more it indicates that the oxygen concentration data at the middle position of the highway tunnel does not conform to the normal oxygen concentration. The greater the difference in oxygen concentration, the worse the ventilation effect in the highway tunnel, and the more abnormal the fan speed.

[0058] (2) Set an oxygen concentration difference threshold. When the oxygen concentration difference value of more than half of the historical sampling times within the preset historical period is greater than or equal to the oxygen concentration difference threshold, it is determined that the fan speed at the current sampling time is abnormal, and an early warning is issued for the fan speed at the current sampling time.

[0059] In one embodiment, the oxygen concentration difference threshold is set to 0.5. This is not limited and can be set according to the specific implementation scenario. When the oxygen concentration difference value of more than half of the historical sampling times within 5 minutes is greater than or equal to 0.5, it is determined that the ventilation effect of the highway tunnel at the current sampling time is poor, the fan speed at the current sampling time is abnormal, and an early warning process is needed for the fan speed at the current sampling time. When the oxygen concentration difference value of more than half of the historical sampling times within 5 minutes is less than the oxygen concentration difference threshold, it is determined that the fan speed at the current sampling time is normal, and no early warning process is needed for the fan speed at the current sampling time.

[0060] It should be noted that if the fan speed at the current sampling time is not within the optimized threshold range, the fan speed data at the current sampling time is determined to be abnormal data. The fan speed data for the next 30 minutes, including the current sampling time, will be continuously monitored. If at least 15 fan speed data are abnormal within the next 30 minutes, it indicates that the fan speed in the next preset period is insufficient to achieve effective ventilation, and the fan speed in the next preset period is determined to be abnormal, and an early warning will be issued for the fan speed in the next preset period. If no at least 15 fan speed data are abnormal within the next 30 minutes, the fan speed in the next preset period is determined to be normal.

[0061] In summary, this embodiment of the invention acquires wind turbine speed data and multidimensional feature data related to wind turbine speed at each historical sampling time within a preset time range including the current sampling time in a highway tunnel, obtaining an initial wind turbine speed data sequence and an initial multidimensional feature data sequence. The initial wind turbine speed data sequence and the initial multidimensional feature data sequence are then preprocessed to obtain the wind turbine speed data sequence and the multidimensional feature data sequence, respectively. Based on the data fluctuation characteristics in the wind turbine speed data sequence, an initial threshold range for the wind turbine speed at the current sampling time is obtained. The wind turbine speed data sequence and the multidimensional feature data sequence are then preprocessed. The system constructs a subsequence of fan speed data and a subsequence of multidimensional feature data at the current sampling time. Based on the correlation between the subsequence of fan speed data and the subsequence of multidimensional feature data, the deviation of fan speed at the current sampling time is obtained. The initial threshold interval is optimized and adjusted based on the deviation of fan speed to obtain an optimized threshold interval. If the fan speed at the current sampling time is within the optimized threshold interval, oxygen concentration data at different locations in the highway tunnel are obtained. Based on the differences in oxygen concentration data at different locations in the highway tunnel, the fan speed at the current sampling time is monitored and warned. This invention first calculates the deviation of the fan speed at the current sampling moment by using fan speed data at each historical sampling moment within a preset time range and multi-dimensional feature data related to the fan speed, optimizes the initial threshold range, and identifies possible mechanical or electrical faults. Then, by using the differences in oxygen concentration data at different locations in the highway tunnel, the ventilation effect of the fan is evaluated, and the fan speed at the current sampling moment is monitored and warned. This not only captures abnormal trends in fan speed but also avoids misjudgments caused by short-term fluctuations in fan speed, ensuring the safe and stable operation of the tunnel, achieving comprehensive monitoring of the fan, and providing accurate warnings of the fan's operating status.

[0062] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A monitoring and early warning system for the operating status of an electromechanical system in a highway tunnel, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the following method: The wind turbine speed data and multidimensional feature data related to the wind turbine speed are obtained from each historical sampling moment within a preset time range including the current sampling moment in the highway tunnel. An initial wind turbine speed data sequence and an initial multidimensional feature data sequence are obtained. The initial wind turbine speed data sequence and the initial multidimensional feature data sequence are preprocessed to obtain the wind turbine speed data sequence and the multidimensional feature data sequence, respectively. Based on the data fluctuation characteristics in the wind turbine speed data sequence, the initial threshold range of the wind turbine speed at the current sampling time is obtained; Construct a subsequence of wind turbine speed data and a subsequence of multidimensional feature data including the wind turbine speed data at the current sampling time in the wind turbine speed data sequence and the multidimensional feature data sequence respectively. Obtain the degree of wind turbine speed deviation at the current sampling time based on the correlation between the wind turbine speed data subsequence and the multidimensional feature data subsequence. Optimize and adjust the initial threshold interval based on the degree of wind turbine speed deviation to obtain an optimized threshold interval. If the fan speed at the current sampling time is within the optimized threshold range, then oxygen concentration data at different locations within the highway tunnel are acquired, and the fan speed at the current sampling time is monitored and warned based on the differences in oxygen concentration data at different locations within the highway tunnel.

2. The monitoring and early warning system for the operation status of the electromechanical system of a highway tunnel according to claim 1, characterized in that, After optimizing the initial threshold range based on the degree of deviation of the wind turbine speed to obtain the optimized threshold range, the process further includes: If the wind turbine speed at the current sampling time is not within the optimized threshold range, the wind turbine speed data at the current sampling time is determined to be abnormal data. The wind turbine speed data within a future preset time period, including the current sampling time, is continuously monitored. When at least a preset number of wind turbine speed data are abnormal data within the future preset time period, an early warning is issued for the wind turbine speed within the future preset time period. If there are no at least a preset number of abnormal fan speed data within the preset future time period, the fan speed within the preset future time period is determined to be normal.

3. The monitoring and early warning system for the operation status of the electromechanical system of a highway tunnel according to claim 1, characterized in that, The step of obtaining the initial threshold range of the wind turbine speed at the current sampling time based on the data fluctuation characteristics in the wind turbine speed data sequence includes: The average value and standard deviation of the wind turbine speed data sequence are obtained. The first difference between the average value and the standard deviation of the first preset multiple is calculated. The first sum of the average value and the standard deviation of the first preset multiple is calculated. The first sum is used as the upper limit and the first difference is used as the lower limit to construct the initial threshold range of the wind turbine speed at the current sampling time.

4. The monitoring and early warning system for the operation status of the electromechanical system of a highway tunnel according to claim 1, characterized in that, The step of obtaining the degree of wind turbine speed deviation at the current sampling time based on the correlation between the wind turbine speed data subsequence and the multidimensional feature data subsequence includes: The multidimensional feature data subsequence is split into multiple one-dimensional feature data subsequences according to the dimension. The Pearson correlation coefficient of the wind turbine speed data subsequence and each one-dimensional feature data subsequence is obtained. Based on the proportion of the Pearson correlation coefficient of each one-dimensional feature data subsequence in all Pearson correlation coefficients, the association weight of each one-dimensional feature data subsequence is obtained. Based on the association weight of each one-dimensional feature data subsequence in the multi-dimensional feature data subsequence, and the data fluctuation characteristics in the wind turbine speed data subsequence and the multi-dimensional feature data subsequence, the degree of wind turbine speed deviation at the current sampling time is obtained.

5. The monitoring and early warning system for the operating status of the electromechanical system of a highway tunnel according to claim 4, characterized in that, The step of obtaining the degree of wind turbine speed deviation at the current sampling time based on the association weight of each one-dimensional feature data subsequence in the multi-dimensional feature data subsequence, and the data fluctuation characteristics in the wind turbine speed data subsequence and the multi-dimensional feature data subsequence, includes: Any historical sampling time within the time range corresponding to the wind turbine speed data subsequence is recorded as the target sampling time. Based on the difference between the wind turbine speed data at the target sampling time and the average value of the wind turbine speed data subsequence, the deviation of the wind turbine speed data at the target sampling time is obtained. The absolute value of the difference between the wind turbine speed data at the target sampling time and the previous sampling time is obtained. The time interval between the target sampling time and the previous sampling time is obtained. The second ratio of the absolute value of the difference to the time interval is calculated. The second summation result of the second ratio of the constant 1 and the second preset multiple is calculated. The first product of the square of the deviation of the wind turbine speed data at the target sampling time and the second summation result is obtained. Obtain the deviation of feature data for each dimension at the target sampling time. Based on the association weight of each one-dimensional feature data subsequence, perform a weighted summation on the deviation of feature data for each dimension at the target sampling time to obtain a first weighted summation result. Perform a weighted summation on the first product and the first weighted summation result to obtain a second weighted summation result. Obtain the arithmetic square root of the second weighted summation result. Substitute the negative of the arithmetic square root of the second weighted summation result into an exponential function with the natural constant as the base to obtain a first exponential function result. Obtain the second difference between the constant 1 and the first exponential function result to obtain the fan speed deviation value at the target sampling time. Obtain the fan speed deviation values ​​for all historical sampling moments within the time range corresponding to the fan speed data subsequence, and obtain the average value of the fan speed deviation values ​​as the degree of fan speed deviation at the current sampling moment.

6. The monitoring and early warning system for the operation status of the electromechanical system of a highway tunnel according to claim 3, characterized in that, The step of optimizing and adjusting the initial threshold range based on the degree of deviation of the wind turbine speed to obtain an optimized threshold range includes: Obtain the third difference between the first difference and the degree of deviation of the fan speed by the third preset multiple, obtain the third sum of the first sum and the degree of deviation of the fan speed by the third preset multiple, and construct the optimization threshold interval with the third sum as the upper limit and the third difference as the lower limit.

7. The monitoring and early warning system for the operation status of the electromechanical system of a highway tunnel according to claim 1, characterized in that, The acquisition of oxygen concentration data at different locations within the highway tunnel includes: Obtain oxygen concentration data at each historical sampling time within a preset historical period, including the current sampling time, at the two port locations and the middle location of the highway tunnel.

8. The monitoring and early warning system for the operation status of the electromechanical system of a highway tunnel according to claim 7, characterized in that, The method of monitoring and issuing early warnings based on the differences in oxygen concentration data at different locations within the highway tunnel, and at the current sampling time, includes: For any historical sampling time within the preset historical period, based on the oxygen concentration data of the two port positions at any historical sampling time, calculate the average oxygen concentration, calculate the absolute value of the oxygen concentration difference between the average oxygen concentration and the oxygen concentration data of the middle position at any historical sampling time, substitute the negative of the absolute value of the oxygen concentration difference into an exponential function with the natural constant as the base, obtain the result of the second exponential function, calculate the difference between the constant 1 and the result of the second exponential function, and obtain the oxygen concentration difference value at any historical sampling time; An oxygen concentration difference threshold is set. When the oxygen concentration difference value of more than half of the historical sampling times within the preset historical period is greater than or equal to the oxygen concentration difference threshold, it is determined that the fan speed at the current sampling time is abnormal, and an early warning is issued for the fan speed at the current sampling time.

9. A monitoring and early warning system for the operating status of an electromechanical system in a highway tunnel according to claim 8, characterized in that, The method of monitoring and issuing early warnings based on the differences in oxygen concentration data at different locations within the highway tunnel, and the monitoring of fan speed at the current sampling time, also includes: When the oxygen concentration difference value of half or more of the historical sampling times within the preset historical period is less than the oxygen concentration difference threshold, it is determined that the fan speed at the current sampling time is normal, and no warning processing is required for the fan speed at the current sampling time.

Images