Computer monitoring system abnormal monitoring method for large-scale power construction project

Abstract

The application relates to the technical field of power facility anomaly monitoring, in particular to a computer monitoring system anomaly monitoring method for large-scale power construction projects, which comprises the following steps: collecting insulator leakage current signals, temperature signals and ultrasonic wave signals, and calculating corresponding energy gradients; calibrating sensor correlation coefficients based on the physical characteristics of insulator materials, and calculating dynamic weights according to the energy gradients, so as to realize dynamic weighting of fault sensitive signals; generating a fusion reference signal through weighted summation; combining device thermophysical parameters, real-time signal characteristics and environmental parameters to construct a dynamic threshold; calculating a signal difference amount of original signals and the fusion signal, and triggering an anomaly early warning if the signal difference amount exceeds the dynamic threshold; the noise influence on a single sensor is suppressed, the signal-to-noise ratio of the fusion signal is effectively improved, the problem that a fixed threshold is prone to cause anomaly missing reports and false reports is avoided, and the insulator anomaly detection precision is improved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of power facility anomaly monitoring, and particularly relates to a computer monitoring system anomaly monitoring method for large-scale power construction projects. BACKGROUND

[0002] Large-scale power construction projects have the characteristics of high voltage level, high equipment density and harsh environmental conditions. Once the key equipment is abnormal, it may cause a chain of failures or even catastrophic consequences. As a core component of the power system, insulators bear the dual functions of insulation and mechanical support, and are widely used in power transmission lines, substations and generator stator windings. The state of the insulator directly affects the reliability of the system. Common abnormalities of insulators include the decrease of insulation resistance caused by pollution deposition, crack damage caused by mechanical stress, material aging caused by corona discharge, and flashover caused by lightning or overvoltage. If these hidden dangers are not found in time, it may lead to line tripping, equipment burning or even large-scale paralysis of the power grid.

[0003] Therefore, the on-line monitoring technology of the insulator state is crucial for large-scale power construction projects. However, the power frequency magnetic field generated by the operation of high-voltage equipment can interfere with the sensor signal, causing random or periodic noise to be mixed into the detection signal, which affects the accurate evaluation of the insulator state. Traditional anomaly monitoring methods usually use single sensor data and use fixed thresholds for anomaly detection, which is difficult to fully capture the abnormal characteristics of the insulator, and the single sensor data is easily affected by noise, which may lead to false negatives and false positives. SUMMARY

[0004] In order to solve the above technical problems, the computer monitoring system anomaly monitoring method for large-scale power construction projects is provided to solve the existing problems.

[0005] The computer monitoring system anomaly monitoring method for large-scale power construction projects provided by the application adopts the following technical scheme:

[0006] One embodiment of the application provides a computer monitoring system anomaly monitoring method for large-scale power construction projects, which comprises the following steps:

[0007] Collecting various types of sensor signals of the insulator at each time, including leakage current signals, temperature signals and ultrasonic signals; collecting humidity signals of the environment at each time;

[0008] Setting a time window at each time, and constructing a signal energy gradient of each type of sensor signal at each time based on the change characteristics of each type of sensor signal in the time window at each time;

[0009] The insulator is subjected to multiple discharge tests, the discharge current of the insulator in the discharge test is collected, and a fault severity sequence of each discharge test is constructed; based on the correlation between the time sequence of each type of sensor signal and the fault severity sequence, and in combination with the signal energy gradient, a dynamic weight coefficient of each type of sensor signal at each time is constructed;

[0010] Based on the leakage current signal, the temperature signal and the ultrasonic signal at each time, and the corresponding dynamic weight coefficient, a fusion reference signal at each time is constructed.

[0011] Based on the material properties of the insulator and the temperature change characteristics at each time, in combination with the values of the multiple sensor signals at each time, a dynamic threshold at each time is constructed.

[0012] The dynamic threshold is compensated based on the environmental humidity signal at each time and the voltage level of the insulator, and a compensated dynamic threshold at each time is constructed.

[0013] Based on the difference between each type of sensor signal and the fusion reference signal at each time, a signal difference amount at each time is constructed; based on the signal difference amount, in combination with the compensated dynamic threshold, insulator anomaly detection is performed.

[0014] In one embodiment, the time window at each time is a time period of a preset time length before each time.

[0015] In one embodiment, the signal energy gradient of each type of sensor signal is expressed as: , wherein, is the signal energy gradient of the temperature at the t-th time; , respectively represent the temperature signal at the first and last time within the time window at the t-th time; represents the time length of the time window;

[0016] Based on the leakage current signal and the ultrasonic signal within each time window, respectively, the signal energy gradient of the leakage current at each time and the signal energy gradient of the ultrasonic wave at each time are calculated in the same way as the signal energy gradient of the temperature at each time.

[0017] In one embodiment, the fault severity sequence is obtained by normalizing the time sequence of the insulator discharge current, and the obtained sequence is taken as the fault severity sequence.

[0018] In one embodiment, the dynamic weight coefficient of each type of sensor signal at each time is obtained by:

[0019] correlation between the time sequence of the temperature signal and each fault severity sequence is calculated, denoted as a first correlation; an average value of all the first correlations of the temperature signal is taken as a correlation coefficient of the temperature signal; and a normalized value of a product between the correlation coefficient of the temperature signal and the signal energy gradient of the temperature at each moment is taken as a dynamic weight coefficient of the temperature signal at each moment;

[0020] Based on the time sequence of the leakage current signal and the ultrasonic signal and the signal energy gradient of each moment, respectively, the dynamic weight coefficients of the leakage current signal and the ultrasonic signal at each moment are obtained in the same way as the dynamic weight coefficient of the temperature signal at each moment.

[0021] In one embodiment, the expression of the fusion reference signal at each moment is: , wherein, is the fusion reference signal at the tth moment; , , are the dynamic weight coefficients of the leakage current, temperature and ultrasonic signal at the tth moment, respectively; , , are the leakage current, temperature and ultrasonic signal at the tth moment, respectively.

[0022] In one embodiment, the expression of the dynamic threshold at each moment is: , wherein, is the dynamic threshold at the tth moment; K represents the thermal conductivity coefficient of the insulator; represents the specific heat capacity of the insulator; represents the temperature change rate at the tth moment; is the leakage current signal at the tth moment; is the ultrasonic signal at the tth moment; is a normalization function;

[0023] The temperature change rate at the tth moment is the ratio of the difference between the temperature at the tth moment and the temperature at the previous moment to the time interval between the two moments.

[0024] In one embodiment, the expression of the compensated dynamic threshold at each moment is: , wherein, represents the compensated dynamic threshold at the tth moment; is the dynamic threshold at the tth moment; is a humidity compensation coefficient; represents the humidity of the environment at the tth moment; represents a preset adjustment coefficient; represents the rated voltage of the insulator; represents a logarithmic function with e as a true number.

[0025] In one embodiment, the expression of the signal difference amount at each time is: , wherein, is the signal difference amount at the tth time; , , is the leakage current, temperature and ultrasonic signal at the tth time, respectively; is the fusion reference signal at the tth time.

[0026] In one embodiment, the insulator anomaly detection is performed based on the signal difference amount and the compensated dynamic threshold, specifically:

[0027] If the signal difference amount at each time is greater than the corresponding compensated dynamic threshold, the insulator is abnormal; otherwise, the insulator is not abnormal.

[0028] The present application has at least the following beneficial effects:

[0029] The present application collects various sensor signals of the insulator at each time, including leakage current signals, temperature signals and ultrasonic signals; based on the change characteristics of various sensor signals in the time window at each time, the signal energy gradient of each type of sensor signal at each time is constructed, and the dynamic weight coefficient of each type of sensor signal at each time is constructed based on the correlation between the time sequence of each type of sensor signal and the discharge current sequence of the insulator, which dynamically reflects the sensitivity difference of each sensor to the fault characteristics; based on the leakage current signal, temperature signal and ultrasonic signal at each time, and the corresponding dynamic weight coefficient, the fusion reference signal at each time is constructed, the signal energy gradient of the multi-sensor is used as the weight, the physical complementarity of different signals is used to generate the fusion signal, the noise influence on a single sensor is suppressed, the signal-to-noise ratio of the fusion signal is effectively improved, and multi-dimensional state perception is realized; the dynamic threshold is constructed based on the material characteristics of the insulator, the real-time signal characteristics and the environmental influence; the signal difference amount at each time is constructed based on the difference between each type of sensor signal at each time and the fusion reference signal; the signal difference amount and the dynamic threshold are compared to determine whether the insulator is abnormal; the problem of false negative and false positive caused by the fixed threshold is avoided, the calculation complexity is reduced, and the insulator anomaly detection accuracy is improved. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the accompanying drawings required by the embodiments or the prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor based on these drawings.

[0031] Figure 1 The flow chart of the computer monitoring system abnormality monitoring method for large-scale power construction projects provided by the present application is shown in the figure.

[0032] Figure 2 The schematic diagram of the acquisition process of the dynamic weight coefficient of the temperature signal is shown in the figure. DETAILED DESCRIPTION

[0033] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined purpose of the application, the specific embodiments, structures, features and effects of the computer monitoring system abnormality monitoring method for large-scale power construction projects according to the present application are described in detail as follows in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0035] The specific scheme of the computer monitoring system abnormality monitoring method for large-scale power construction projects provided by the present application is described in detail below in combination with the accompanying drawings.

[0036] The computer monitoring system abnormality monitoring method for large-scale power construction projects provided by one embodiment of the present application.

[0037] Specifically, the computer monitoring system abnormality monitoring method for large-scale power construction projects is provided as follows, please refer to Figure 1 The method comprises the following steps:

[0038] Step S1, collecting various types of sensor signals of insulators at each time, including leakage current signals, temperature signals and ultrasonic signals; collecting humidity signals of the environment at each time.

[0039] The insulation sub abnormality is usually accompanied by synchronous changes of electrical parameters (leakage current), thermal characteristics (local temperature rise), and mechanical vibration (discharge noise). A single sensor, such as a leakage current sensor, cannot comprehensively capture the fault characteristics and is easily disturbed by the environment. The application solves the problem of one-sided information and easy disturbance of a single sensor by monitoring the insulation sub state in multiple dimensions.

[0040] One set of sensors is installed on the wire side (high potential) and the grounding side (low potential) of the insulator string to monitor the overall potential distribution change of the insulator string. Each set of sensors includes one leakage current sensor, one temperature sensor, one ultrasonic sensor, and one humidity sensor.

[0041] The application collects the leakage current signal, temperature signal, and ultrasonic signal of the insulator through the leakage current sensor, temperature sensor, and ultrasonic sensor, specifically:

[0042] (1) Leakage current refers to the current formed by the current passing through the small conductive path on the surface or internal insulating medium of the insulator under working voltage. When there is damage to the insulator shed, aging of the coating (such as brittle silicon rubber of composite insulators), or uneven distribution of contamination, local electric field concentration (such as the edge of the shed or the tip of the crack) will cause corona discharge or surface micro-discharge. These discharge phenomena will ionize the air to form an ion current, forming a pulse-type leakage current with a small average amplitude but containing early characteristics of insulation degradation.

[0043] For leakage current signal collection, the application uses a through-type Rogowski coil (bandwidth 0~100kHz) to collect leakage current signals, and the data collection time interval of the leakage current signal is set to 1ms. As other embodiments of the application, the implementer can set the data collection time interval of the leakage current signal according to the actual situation. It should be noted that the implementer can also use other leakage current sensors to collect leakage current signals, which are not specifically limited by the application.

[0044] The average value of the leakage current signal collected by the leakage current sensor on the wire side and the grounding side at each time is taken as the leakage current signal of the insulator at each time.

[0045] A second-order Butterworth low-pass filter (cutoff frequency 20kHz) is used to filter the leakage current signal to suppress high-frequency noise generated by ultrahigh voltage corona; and a signal amplifier is used to amplify the filtered leakage current signal, and the gain effect of the amplifier in the application is 100 times, which improves the detection precision of small current.

[0046] (2) Temperature signal change and insulator abnormality exist strong correlation, when the insulator surface appears slight contamination or internal crack, the leakage current may not have significantly increased, but the discharge generated Joule heat will cause local temperature rise, leakage current reflects the discharge intensity, temperature reflects the discharge duration effect.

[0047] For the collection of temperature signals, the application adopts a single-point infrared temperature measurement module (Melexis MLX90614) to collect temperature signals, and the data collection time interval of the temperature signals is set to 1s. As other embodiments of the application, the implementer can set the data collection time interval of the temperature signals according to the actual situation. It should be noted that the implementer can also use other temperature sensors to collect temperature signals according to the actual situation, and the application does not make specific limitations.

[0048] The average of the temperature signals collected by the temperature sensors on the conductor side and the ground side at each time is taken as the temperature signal of the insulator at each time.

[0049] (3) The ultrasonic signal is a key feature of the insulator discharge type abnormality. Local discharge caused by insulator surface contamination, cracks or internal defects will produce wideband acoustic signals, and the 20kHz~100kHz ultrasonic component, especially the ultrasonic component near 40kHz, is an important carrier of discharge energy. Unlike environmental noise, such as wind and rain, bird activity, the energy is concentrated below 20kHz, the ultrasonic signal amplitude is positively correlated with the discharge intensity, and can reflect the discharge initiation and development process.

[0050] For the collection of ultrasonic signals, the application adopts a narrowband piezoelectric ceramic sensor (center frequency 40kHz) to collect ultrasonic signals, and the data collection time interval of the ultrasonic signals is set to 50ms. As other embodiments of the application, the implementer can set the data collection time interval of the ultrasonic signals according to the actual situation. It should be noted that the implementer can use other ultrasonic sensors to collect ultrasonic signals according to the actual situation, and the application does not make specific limitations.

[0051] The average of the ultrasonic signals collected by the ultrasonic sensors on the conductor side and the ground side at each time is taken as the ultrasonic signal of the insulator at each time.

[0052] The ultrasonic signal is a key to the insulator discharge type abnormality. A band-pass filter is used to filter the ultrasonic signal, and the pass band of the band-pass filter in the application is 35~45kHz, excluding the influence of wind and rain noise and power frequency harmonic; an automatic gain control (AGC) circuit is used to automatically control the gain of the ultrasonic signal, dynamically adapting to the amplitude change of the discharge signal.

[0053] In addition, the humidity signal of the environment around the insulator is collected by the humidity sensor, and the data collection time interval of the humidity signal is set to 1s. Although the insulator anomaly does not cause humidity change, the environmental humidity will affect the resistance of the insulator, causing errors.

[0054] Due to different acquisition frequencies of various sensors, time synchronization is performed by outputting a 1PPS pulse signal by the GPS module, data points are marked by time stamps, linear interpolation is adopted to synchronize the low-frequency signal to the high-frequency time sequence, and multi-signal time alignment is ensured.

[0055] In a strong electromagnetic interference environment, the leakage current sensor is prone to high-frequency oscillation or baseline drift due to electromagnetic induction coupling, the rear-end amplification circuit of the ultrasonic sensor may be affected by electric field coupling to reduce the signal-to-noise ratio, and the readout circuit and analog-to-digital conversion link of the temperature sensor may be affected by magnetic field interference to reduce the temperature measurement accuracy; however, due to differences in interference coupling paths, sensitive frequency bands and physical principles of different sensors, strong electromagnetic interference is difficult to simultaneously cause serious impact on all sensors. By using multi-sensor fusion technology, the disturbed channels can be compensated by undistorted signals, the monitoring reliability in a complex electromagnetic environment can be significantly improved, and the complementation of multi-dimensional signals and the superposition of anti-interference capabilities can be realized.

[0056] In order to facilitate subsequent processing, the leakage current signal, the temperature signal, the ultrasonic signal and the humidity signal at all times are normalized by the Z-score normalization algorithm, so as to eliminate the dimensional influence.

[0057] In step S2, the time window of each time is set, and the signal energy gradient of each type of sensor signal at each time is constructed based on the change characteristics of each type of sensor signal in the time window of each time.

[0058] In insulator anomaly monitoring, the mutation characteristics of the signal are the key to fault warning. Partial discharge can cause instantaneous increase of leakage current and sharp rise of temperature in the discharge area, and these changes are manifested as rapid rise of signal power. The traditional method directly uses the absolute value or static statistics of the signal, such as leakage current effective value and average value, for anomaly monitoring, but it is difficult to capture the power change in a short time and is easily disturbed by slow-changing environmental noise.

[0059] Taking the temperature signal as an example, the signal energy gradient of the temperature at each time is calculated by the difference between the temperature signals at the start and end times in the time window, reflecting the real-time change rate of the temperature signal power, and the expression is: , in the formula, is the signal energy gradient of the temperature at the t time; , and represent the temperature signals at the first and last times in the time window at the t time in the temperature signal time sequence, respectively. represents the length of the time window, preferably, in the embodiment of the present application, the value of T is set to 10 ms, covering the typical duration of a discharge pulse. As other embodiments of the present application, the implementer can set the value of T according to actual conditions. In the present application, the time window of each time point is a time period of a preset length before each time point, and in the embodiment of the present application, the preset length is T.

[0060] The signal energy gradient of the leakage current at each time point and the signal energy gradient of the ultrasonic wave at each time point are calculated based on the leakage current signal and the ultrasonic wave signal in each time window, respectively, by using the same calculation method as the signal energy gradient of the temperature at each time point.

[0061] The present application uses a differential approximation to replace integration and differentiation, reducing the demand for computing power. The energy gradient is essentially the time rate of change of signal power, reflecting the increment of signal energy per unit time. When a fault occurs, the energy gradient of the signal will have a significant positive peak, while in normal operation, it remains low and fluctuates. The greater the energy gradient, the more likely it is that the signal comes from a fault feature rather than noise, and a higher weight will be assigned in the subsequent steps to enhance the ability of the fusion signal to represent faults. Avoiding the non-stationary characteristics of signals affected by load fluctuations and weather conditions, the energy gradient can dynamically track the effective changes of the signal, avoiding the hysteresis of fixed thresholds.

[0062] In step S3, a plurality of discharge tests are performed on the insulator, and the discharge current of the insulator in the discharge test is collected to construct a fault severity sequence of each discharge test; based on the correlation between the time sequence of each type of sensor signal and the fault severity sequence, and in combination with the signal energy gradient, a dynamic weight coefficient of each type of sensor signal at each time point is constructed.

[0063] In multi-sensor fusion monitoring, different sensors have natural differences in sensitivity to the same fault. The traditional scheme uses fixed weights, which cannot dynamically adjust the weights according to real-time working conditions, which may result in key signals being overwhelmed by noise.

[0064] ​​​First, the correlation coefficients between various sensor signals and insulator faults are analyzed. Specifically, a discharge test is performed on the insulator, and the discharge current of the insulator at each time during the discharge test is collected. The time series of the discharge current is normalized to obtain a sequence of fault severity. The discharge test is performed multiple times to obtain a fault severity sequence for each discharge test. The Pearson correlation coefficient between the time series of the temperature signal and each fault severity sequence is calculated and denoted as a first correlation. The average of all first correlations of the temperature signal is taken as the correlation coefficient of the temperature signal. Furthermore, the correlation coefficients of the leakage current signal and the ultrasonic signal are obtained in the same way as the correlation coefficient of the temperature signal based on the time series of the leakage current signal and the ultrasonic signal, respectively. The correlation coefficient represents the degree of association between the sensor signal and the physical mechanism of the insulator fault. Preferably, in the embodiments of the present application, the number of discharge tests is set to 3. As other embodiments of the present application, the implementer can set the number of discharge tests according to actual conditions.

[0065] The Pearson correlation coefficient is a known technology, and the specific process is not described again. It should be noted that for the correlation between the time series of the temperature signal and the fault severity sequence, the present application only provides one correlation calculation method. There are many existing correlation calculation methods, and the implementer can also use other correlation algorithms to calculate the correlation between the time series of the temperature signal and the fault severity sequence. The present application does not make specific limitations.

[0066] Furthermore, the product of the signal energy gradient of each type of sensor signal at each time and the correlation coefficient is calculated and denoted as a first product. The normalized value of the first product is taken as the dynamic weight coefficient of each type of sensor signal at each time.

[0067] Preferably, in the embodiments of the present application, the normalization method of the first product is as follows: the sum of the first products of the leakage current, temperature, and ultrasonic signals at any time is calculated and denoted as a first sum. The ratio of the first product of each type of sensor at the any time to the first sum is taken as the dynamic weight coefficient of each type of sensor at the any time.

[0068] The inherent physical characteristics of the sensor, i.e., sensitivity to a specific fault, are considered, and the real-time signal change characteristics, i.e., the current fault intensity is reflected through the energy gradient. Taking the leakage current sensor as an example, the dynamic weight coefficient is calculated, and the expression is as follows:

[0069] Through adaptive adjustment of sensor weights, when the energy gradient of a certain sensor signal suddenly increases, its weight is also increased synchronously, ensuring that the fusion signal preferentially reflects the fault characteristics of the sensor signal. Low weight is assigned to sensors with low energy gradient and weak physical correlation, reducing the impact of noise. The problem of traditional fixed weights being unable to adapt to changes in working conditions and weak anti-interference ability is solved. The inherent characteristics of the sensor are combined with real-time fault characteristics to achieve intelligent weighting of multi-sensor data, enabling the fusion signal to dynamically focus on the current most critical monitoring indicators, significantly improving the fault recognition ability in complex environments.

[0070] Step S4, based on the leakage current signal, temperature signal and ultrasonic signal at each time, and the corresponding dynamic weight coefficient, a fusion reference signal at each time is constructed.

[0071] According to different sensor signals and dynamic weights, a fusion reference signal at each time is generated, and the expression is: In the formula, is the fusion reference signal at the t time; , , are the dynamic weight coefficients of the leakage current, temperature and ultrasonic signals at the t time, respectively; , , are the leakage current, temperature and ultrasonic signals at the t time, respectively. The fusion reference signal is generated by weighted summation to suppress single sensor noise interference.

[0072] Step S5, based on the material characteristics of the insulator and the temperature change characteristics at each time, and combining the values of various sensor signals at each time, a dynamic threshold at each time is constructed.

[0073] The prior art mainly uses a single sensor to collect data and sets a fixed threshold, without considering individual differences of equipment. The heat capacity and insulation characteristics of insulators of different materials are different, and the fixed threshold cannot be accurately adapted. The increase in humidity will cause the surface resistivity of the insulator to decrease, and the fixed threshold is prone to false alarms in humid weather.

[0074] The present application sets a dynamic threshold through physical device parameters and real-time environmental data, so that the threshold is dynamically adjusted according to the individual characteristics of the equipment, the load change and the environmental conditions, solving the problem that the traditional fixed threshold cannot adapt to environmental changes. The expression of the dynamic threshold is: In the formula, is the dynamic threshold at the t time; K represents the thermal conductivity coefficient of the insulator; represents the specific heat capacity of the insulator; represents the temperature change rate at the t time; is the leakage current signal at the t time; is the ultrasonic signal at the t time; is a normalization function.

[0075] It should be noted that the normalization function in the above formula can be , is an exponential function with a natural constant as the base number; the implementer can also normalize in other ways, which is not specifically limited in the present application. K represents the heat conduction capacity of the insulator material, reflects the heat flow when the temperature gradient per unit time per unit area is 1K, and is directly related to the material type, which can be directly obtained by consulting the material manual. For example, the thermal conductivity of a ceramic insulator is , and the thermal conductivity of a composite insulator is . It quantifies the heat dissipation efficiency of the device. The smaller the thermal conductivity (such as a composite insulator), the higher the internal loss power corresponding to the same temperature rise, the higher the fault sensitivity, and the smaller the dynamic threshold should be. The larger the thermal conductivity, the larger the dynamic threshold.

[0076] represents the heat storage capacity of the material, reflects the heat required to raise the temperature of unit mass of material by 1K, and is related to the material and structure of the insulator. The specific heat capacity of the insulator can be obtained by consulting the material manual, such as a ceramic insulator , and a composite insulator . The larger the specific heat capacity of the material (such as a composite insulator), the slower the temperature change, and more energy is required to trigger the threshold, avoiding false positives. The larger the specific heat capacity, the larger the dynamic threshold.

[0077] represents the temperature change value of the insulator surface per unit time. The difference between the temperature at time t and the temperature at the previous time is calculated, and the ratio of the difference to the time interval between the two times is taken as the temperature change rate at time t. The rapid temperature rise caused by partial discharge or poor contact is captured, avoiding threshold misjudgment.

[0078] Step S6, compensating the dynamic threshold based on the environmental humidity signal and the voltage grade of the insulator at each time, and constructing the compensated dynamic threshold at each time.

[0079] In a high humidity environment, water in the air forms a water film on the surface of the insulator, especially after the pollution particles absorb moisture, which will significantly reduce the surface resistivity, causing the leakage current to increase. The traditional fixed threshold cannot adapt to the normal signal fluctuation caused by humidity changes, and is easy to misjudge as insulation degradation in humid weather (such as misjudging the increase in leakage current caused by moisture as pollution discharge), or miss early faults in dry environments (such as not adjusting the threshold dynamically with the decrease in humidity, resulting in a small leakage current not being identified).

[0080] Based on the dielectric physical theory, the influence of humidity on the surface conductive characteristics of the insulator can be quantified by an exponential model. The humidity compensation coefficient is constructed in the present application, and the expression is: , wherein, represents a preset adjustment coefficient, used to quantify the proportional relationship of the humidity sensitivity of the voltage level, and the value range is 0.03-0.07, preferably, the value of is set to 0.05 in the embodiment of the present application; represents the rated voltage of the insulator; represents the logarithmic function with e as the true number. Since the higher the voltage level is, the greater the electric field intensity on the surface of the insulator is, and the influence of humidity change on the surface conductive characteristics is more significant, therefore, by the logarithmic function, the compensation coefficient is increased with the increase of the rated voltage, so as to dynamically adjust the response amplitude of the threshold to humidity, and ensure that the equipment of different voltage levels can obtain accurate environmental compensation.

[0081] Further, the dynamic threshold after compensation at each moment is constructed, and the expression is: , wherein, represents the dynamic threshold after compensation at the t th moment, represents the humidity of the environment at the t th moment. The greater the value is, the more significant the normal fluctuation range of the sensor signal under the current working condition due to the influence of environmental factors is, the signal is allowed to fluctuate in a larger range without triggering an abnormal judgment, and the misjudgment caused by environmental noise is avoided; on the contrary, it indicates that the current working condition is stable, and the signal fluctuation should be in a smaller range, so as to be more sensitive to the deviation of the signal.

[0082] Step S7, based on the difference between each type of sensor signal and the fusion reference signal at each moment, the signal difference quantity at each moment is constructed; based on the signal difference quantity, the dynamic threshold after compensation is combined to perform insulator abnormality detection.

[0083] Based on the difference between each type of sensor signal and the fusion reference signal at each moment, the signal difference quantity between the original signal and the fusion reference signal at each moment is calculated, and preferably, in the embodiment of the present application, the expression of the signal difference quantity at each moment can be: , wherein, is the signal difference quantity between the original signal and the fusion reference signal at the t th moment; , , are the leakage current, temperature and ultrasonic signal at the t th moment, respectively; is the fusion reference signal at the t th moment.

[0084] In other embodiments of the present application, the signal difference amount at each time point can be the average value of the leakage current, temperature, and the absolute value of the difference between the ultrasonic signal and the fusion reference signal at each time point.

[0085] The fusion reference signal is a comprehensive representation of multiple sensors, and the difference between the original signal and the fusion reference signal represents the deviation of the original signal from the fusion reference signal. When a sensor is abnormal due to failure or interference, the difference between the original signal and the reference signal will significantly increase, while other sensors that are not interfered can still ensure the reliability of the reference signal. The signal difference amount is compared with the threshold value to determine whether the insulator is abnormal.

[0086] The multiple sensor signals maintain a stable cooperative relationship due to physical correlation, and the signal difference amount is at a low level. When the insulator is abnormal, one or more sensor signals deviate from the reference, and the signal difference amount exceeds the threshold value.

[0087] If the signal difference amount between the original signal and the fusion reference signal at each time point is greater than the dynamic threshold value after compensation at that time point, it indicates that the insulator is abnormal, and the relevant maintenance personnel are notified to detect and maintain the insulator. If the signal difference amount between the original signal and the fusion reference signal at each time point is less than or equal to the dynamic threshold value after compensation at that time point, it indicates that the insulator is not abnormal.

[0088] The acquisition process of the dynamic weight coefficient of the temperature signal is shown in Figure 2 .

[0089] In summary, the embodiments of the present application acquire various sensor signals of the insulator at each time point, including leakage current signals, temperature signals, and ultrasonic signals; construct the signal energy gradient of each type of sensor signal at each time point based on the change characteristics of each type of sensor signal in the time window at each time point; construct the dynamic weight coefficient of each type of sensor signal at each time point based on the correlation between the time sequence of each type of sensor signal and the discharge current sequence of the insulator, which dynamically reflects the sensitivity difference of each sensor to the fault characteristics; construct the fusion reference signal at each time point based on the leakage current signal, the temperature signal, and the ultrasonic signal at each time point, and the corresponding dynamic weight coefficient; generate a fusion signal by using the physical complementarity of different signals, suppress the noise influence on a single sensor, effectively improve the signal-to-noise ratio of the fusion signal, and realize multi-dimensional state perception by using the signal energy gradient of multiple sensors as the weight; construct a dynamic threshold value based on the material characteristics of the insulator, the real-time signal characteristics, and the environmental influence; construct the signal difference amount at each time point based on the difference between each type of sensor signal and the fusion reference signal at each time point; compare the signal difference amount with the dynamic threshold value to determine whether the insulator is abnormal; avoid the problem of false negatives and false positives caused by a fixed threshold value, reduce the computational complexity, and improve the insulator abnormality detection accuracy.

[0090] It should be noted that the above-mentioned order of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the above describes the specific embodiments of the present application. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0091] Each of the embodiments in the present application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments.

[0092] The above-described embodiments are only used to illustrate the technical solutions of the present application, but not limit them; modifying the technical solutions described in the above embodiments, or equivalently replacing some technical features, does not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for monitoring abnormalities in a computer monitoring system for large-scale power plant construction projects, characterized by, The method comprises the following steps: Collecting various sensor signals of the insulator at each time, including leakage current signals, temperature signals, and ultrasonic signals; collecting humidity signals of the environment at each time; Setting a time window at each time, and constructing a signal energy gradient of each type of sensor signal at each time based on the change characteristics of the various sensor signals in the time window at each time; Performing multiple discharge tests on the insulator, collecting the discharge current of the insulator during the discharge test, and constructing a fault severity sequence of each discharge test; based on the correlation between the time sequence of each type of sensor signal and the fault severity sequence, and in combination with the signal energy gradient, a dynamic weight coefficient of each type of sensor signal at each time is constructed; Based on the leakage current signal, the temperature signal, and the ultrasonic signal at each time, and the corresponding dynamic weight coefficient, a fusion reference signal at each time is constructed; Based on the material characteristics of the insulator and the temperature change characteristics at each time, in combination with the values of various sensor signals at each time, a dynamic threshold at each time is constructed; Based on the environmental humidity signal at each time and the voltage level of the insulator, the dynamic threshold is compensated to construct a compensated dynamic threshold at each time; Based on the difference between each type of sensor signal and the fusion reference signal at each time, a signal difference amount at each time is constructed; based on the signal difference amount, in combination with the compensated dynamic threshold, insulator anomaly detection is performed.

2. The computer monitoring system abnormality monitoring method for large-scale power plant construction work according to Claim 1, wherein The time window at each time is a time period of a preset length before each time.

3. The computer monitoring system abnormality monitoring method for large-scale power plant construction projects according to Claim 1, wherein The expression of the signal energy gradient of each type of sensor signal is: wherein is the signal energy gradient of the temperature at time t; 、 denote the temperature signal at the first and last time within the time window at time t, respectively; denotes the length of the time window. Based on the leakage current signal and the ultrasonic signal in each time window, the signal energy gradient of the leakage current at each time and the signal energy gradient of the ultrasonic wave at each time are calculated in the same way as the signal energy gradient of the temperature at each time.

4. The computer monitoring system abnormality monitoring method for large-scale power plant construction projects according to Claim 1, wherein The acquisition process of the fault severity sequence is: normalizing the time sequence of the insulator discharge current to obtain a sequence as the fault severity sequence.

5. The computer monitoring system abnormality monitoring method for large-scale power plant construction projects according to Claim 1, wherein The acquisition process of the dynamic weight coefficient of each type of sensor signal at each time is: Calculate the correlation between the time sequence of the temperature signal and each fault severity sequence, denoted as the first correlation; the average of all the first correlations of the temperature signal is taken as the correlation coefficient of the temperature signal; the normalized value of the product between the correlation coefficient of the temperature signal and the signal energy gradient of the temperature at each time is taken as the dynamic weight coefficient of the temperature signal at each time; Based on the time sequence of the leakage current signal and the ultrasonic signal and the corresponding signal energy gradient at each time, the dynamic weight coefficients of the leakage current signal and the ultrasonic signal at each time are obtained in the same way as the dynamic weight coefficient of the temperature signal at each time.

6. The computer monitoring system abnormality monitoring method for large-scale power plant construction projects according to Claim 1, wherein The expression of the fusion reference signal at each time is: , wherein, is the fusion reference signal at the tth moment; 、 、 are dynamic weight coefficients of the leakage current, temperature and ultrasonic signal at the tth moment, respectively; 、 、 are the leakage current, temperature and ultrasonic signal at the tth moment, respectively.

7. The computer monitoring system abnormality monitoring method for large-scale power plant construction projects according to Claim 1, wherein The expression of the dynamic threshold at each time is: wherein, Kt is the dynamic threshold value at the tth moment; K represents the thermal conductivity coefficient of the insulator; Ct is the specific heat capacity of the insulator; αt is the temperature change rate at the tth moment; It is the leakage current signal at the tth moment; Ut is the ultrasonic signal at the tth moment; is a normalization function; Wherein, the temperature change rate at the tth time is the difference between the temperature at the tth time and the temperature at the previous time divided by the time interval between the two times.

8. The computer monitoring system abnormality monitoring method for large-scale power plant construction projects according to Claim 1, wherein The expression of the compensated dynamic threshold value at each time is: In the formula, Compensated dynamic threshold value at the tth time; Dynamic threshold value at the tth time; Humidity compensation coefficient; Humidity of the environment at the tth time; Pre-set adjustment coefficient; Rated voltage of the insulator; Logarithmic function with e as the true number.

9. The computer monitoring system abnormality monitoring method for large-scale power plant construction projects according to Claim 1, wherein The expression of the signal difference amount at each time is: , wherein, is a signal difference amount at the tth moment; , , are a leakage current, a temperature, and an ultrasonic signal at the tth moment, respectively; is a fusion reference signal at the tth moment.

10. The computer monitoring system abnormality monitoring method for large-scale power plant construction projects according to Claim 1, wherein Based on the signal difference amount, in combination with the compensated dynamic threshold, insulator anomaly detection is performed, specifically: If the signal difference at each moment is greater than the corresponding compensated dynamic threshold, the insulator appears abnormal; otherwise, the insulator does not appear abnormal.

Images