Monitoring method and device for electric equipment in machine room and electronic equipment

Abstract

The invention belongs to the technical field of electric measurement, and particularly discloses a monitoring method and device for electric equipment in a machine room and electronic equipment. Constructing a sliding time window to perform time window segmentation processing on the first monitoring data to obtain a monitoring sequence; the instantaneous power of the cooling water pump is calculated in real time based on the first monitoring data, a first power sequence in the same time window is obtained, the power change rate of the cooling water pump is calculated according to the first power sequence, a power change rate sequence is obtained, and the power abnormity monitoring value in each time window is calculated through the power change rate sequence; the first monitoring abnormal feature and the second monitoring abnormal feature of the cooling water pump are analyzed and calculated, and through multi-index fusion and intelligent data analysis, energy consumption and maintenance risks are effectively reduced while safe operation of machine room power supply equipment is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical measurement. More specifically, the present invention relates to a monitoring method, device, and electronic device for electrical equipment in a computer room. Background Art

[0002] In a high-density production environment, multiple high-performance cooling towers are used to ensure the temperature control of key equipment in the refrigeration machine room. Existing literature (Mo Zifang. Research on the Efficient Operation of the Refrigeration Machine Room System Based on the Operating Parameters of Cooling Towers [D]. Guangzhou University, 2024. DOI: 10.27040 / d.cnki.ggzdu.2024.000711.) takes the air-conditioning refrigeration machine room of a certain condiment processing factory as the research object. For example, Figure 2 As the two-dimensional floor plan of the refrigeration machine room system in the energy management system, when analyzing the energy-saving optimization of the operation of the cooling tower in the refrigeration machine room system under the condition of meeting the cooling load at the air-conditioning terminal, the aim is to achieve low-energy consumption operation in the optimized refrigeration machine room system and provide a reference for the optimized control strategy of the refrigeration machine room system.

[0003] When there are fluctuations in the power supply system of the cooling tower, resulting in significant changes in current and power, the existing monitoring system fails to capture the instantaneous power fluctuations in a timely manner due to its slow response speed. The cooling water pump suddenly enters an overload state due to unstable voltage, and the power surges. However, the sampling frequency of the traditional monitoring system is low or the data processing delay is long, and it fails to identify this abnormal fluctuation in a timely manner. During the process of the equipment being in an overload state, the system fails to trigger an early warning or alarm at the real-time data level. At this time, the system response is not timely, and the overload state will continue for a period of time, which may cause the cooling water pump to overheat and even damage key components, thereby affecting the normal operation of the entire cooling system, increasing the difficulty of maintenance, and even causing production losses due to shutdown and repair. At the same time, due to excessive energy consumption and the system not giving an early warning, the refrigeration load exceeds the capacity, which may lead to abnormal temperature control of the entire computer room, increasing power waste. To solve the above problems, a technical solution is provided. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides a monitoring method, device, and electronic device for electrical equipment in a computer room, which solves the problems of abnormal temperature control of the entire computer room that may be caused by excessive energy consumption and the system not giving an early warning, and the refrigeration load exceeding the capacity, by analyzing the first monitoring abnormal feature and the second monitoring abnormal feature of the cooling water pump.

[0005] To achieve the above object, the present invention provides the following technical solutions: A monitoring method for electrical equipment in a computer room, comprising the following steps: Step 1: The monitoring data of the cooling tower are collected in real time through the sensor network and the power factor detection module, and the monitoring data are filtered, smoothed and normalized to obtain the first monitoring data. A sliding time window is constructed to perform time window segmentation processing on the first monitoring data to obtain the monitoring sequence , where is the first monitoring data within the i-th time window, is the number of time window segments, , where is the j-th first monitoring data, is the number of first monitoring data in Step 2: Based on the first monitoring data, the instantaneous power of the cooling water pump is calculated in real time to obtain the first power sequence within the same time window , where is the j-th instantaneous power, is the m-th instantaneous power. According to the first power sequence, the power change rate of the cooling water pump is calculated to obtain the power change rate sequence , where is the j-th power change rate, is the (m - 1)-th power change rate. The power anomaly monitoring values within each time window are calculated through the power change rate sequence; the power anomaly monitoring values include the mean and the standard deviation; Step 3: By extracting the temperature data from the first monitoring data, the temperature change rate within each time window is calculated based on the temperature data to generate the temperature change rate sequence, and the first monitoring anomaly feature of the cooling water pump is calculated according to the temperature change rate sequence; Step 4: According to the clustering distribution result among the power change rates within each time window, the second monitoring anomaly feature of the cooling water pump is obtained; Step 5: The first monitoring anomaly feature and the second monitoring anomaly feature are obtained and compared with the preset anomaly threshold, and an anomaly instruction is output according to the comparison result.

[0006] As a further solution of the present invention, in Step 1, the monitoring data are collected in real time through the sensor network and the power factor detection module. The sensor network includes a voltage sensor, a current sensor and a temperature sensor. The voltage data of the cooling water pump are obtained in real time through the voltage sensor, the current data of the cooling water pump are obtained in real time through the current sensor, and the temperature data of the cooling water pump are obtained in real time through the temperature sensor. The power factor detection module is used to monitor the power factor of the cooling water pump.

[0007] In Step 2, the instantaneous power of the cooling water pump is calculated in real time based on the first monitoring data, and the calculation formula of the instantaneous power is; ; In the formula: is the instantaneous power at time t, is the voltage data at time t, is the current data at time t, is the power factor at time t; is the j-th power change rate, and the calculation formula is: ; In the formula: is the j-th instantaneous power, is the (j + 1)-th instantaneous power, is the time interval between adjacent sampling points; Calculate the mean value and standard deviation within each time window through the power change rate sequence respectively, and the specific formula is: ; ; In the formula: is the mean value corresponding to the sequence, is the standard deviation corresponding to the sequence.

[0008] As a further solution of the present invention, in step 3, calculate the first monitoring abnormal feature of the cooling water pump according to the temperature change rate sequence, and the specific steps are: Step 31, extract the temperature data from the first monitoring data , calculate the temperature change rate within each time window according to the temperature data generate the temperature change rate sequence ; Step 32, calculate the first monitoring abnormal feature of the cooling water pump according to the temperature change rate sequence, determine the temperature change rates of three consecutive sampling points within the time window, take the temperature change rate at the current moment minus twice the temperature change rate at the previous moment, and then add the temperature change rate at the previous moment as the numerator; Step 33, take the product of the reciprocal of the square of the time interval between adjacent sampling points and the numerator as the first monitoring abnormal feature .

[0009] As a further solution of the present invention, in step 4, obtain the second monitoring abnormal feature of the cooling water pump according to the clustering distribution result between the power change rates within each time window, and the specific steps are: Step 41, arrange the power change rate sequence composed of the power change rates within each time window in chronological order, and automatically divide the data in the power change rate sequence into several clustering clusters according to the clustering algorithm without presetting the number of clustering clusters; Step 42: For each data point in the power change rate sequence, use the fixed-length time period that contains this data point and is centered at the moment it is located as the observation time window. Step 43: Based on each data point in the power change rate sequence, construct a sliding time window with a fixed size centered on it, and calculate the second monitoring anomaly feature of the cooling water pump based on the distribution of elements within the observation time window of each power change rate and the distribution characteristics of the data within the clustering clusters.

[0010] As a further solution of the present invention, in Step 43, the second monitoring anomaly feature of the cooling water pump is calculated based on the distribution of elements within the observation time window of each power change rate and the distribution characteristics of the data within the clustering clusters. The specific steps are as follows: According to the obtained clustering results within each observation time window, count the number of different clustering clusters to which all the power change rates within this observation time window belong, calculate the power anomaly monitoring value of the power change rates within the observation time window, calculate the difference between the mean and variance in the power anomaly monitoring values, and use the product of the number of clustering clusters and the difference as the numerator. For each power change rate within the observation time window, count the frequency of its occurrence in the entire power change rate sequence, and accumulate all the frequencies to obtain the cumulative frequency of the data within this observation time window in the global difference sequence. Use the normalized product of the numerator and the reciprocal of the cumulative frequency in the global difference sequence as the second monitoring anomaly feature of the cooling water pump.

[0011] A monitoring device for electrical equipment in a computer room includes a data acquisition module, a data processing module, a first monitoring anomaly analysis module, a second monitoring anomaly analysis module, and an alarm and control module. The data acquisition module is connected to the data processing module, the data processing module is respectively connected to the first monitoring anomaly analysis module and the second monitoring anomaly analysis module, and the first monitoring anomaly analysis module and the second monitoring anomaly analysis module are respectively connected to the alarm and control module. The data acquisition module is used to collect the monitoring data of the cooling tower in real time through a sensor network and a power factor detection module, perform filtering, smoothing, and normalization processing on the monitoring data to obtain the first monitoring data, and construct a sliding time window to perform time window segmentation processing on the first monitoring data to obtain a monitoring sequence. The data processing module is used to calculate the instantaneous power of the cooling water pump in real time based on the first monitoring data to obtain the first power sequence within the same time window, calculate the power change rate of the cooling water pump according to the first power sequence to obtain the power change rate sequence, and calculate the power anomaly monitoring value within each time window through the power change rate sequence. The first monitoring anomaly analysis module is used to extract temperature data from the first monitoring data, calculate the temperature change rate within each time window based on the temperature data to generate a temperature change rate sequence, and calculate the first monitoring anomaly feature of the cooling water pump according to the temperature change rate sequence; The second monitoring anomaly analysis module obtains the second monitoring anomaly feature of the cooling water pump according to the clustering distribution result among the power change rates within each time window; The alarm and control module is used to obtain the first monitoring anomaly feature and the second monitoring anomaly feature, compare them with a preset anomaly threshold, and output an anomaly existence instruction according to the comparison result.

[0012] An electronic device includes: a memory; a processor; and a computer program; wherein, the computer program is stored in the memory and is configured to be executed by the processor to implement the above-mentioned monitoring method for the power-consuming equipment in the computer room.

[0013] A monitoring method, device and electronic device for power-consuming equipment in a computer room provided by the present invention. The present invention acquires the monitoring data of the cooling tower in real time through a sensor network and a power factor detection module, constructs a sliding time window to perform time window segmentation processing on the first monitoring data to obtain a monitoring sequence; calculates the instantaneous power of the cooling water pump in real time based on the first monitoring data to obtain a first power sequence within the same time window, calculates the power change rate of the cooling water pump according to the first power sequence and obtains a power change rate sequence, calculates the power anomaly monitoring value within each time window through the power change rate sequence, analyzes and calculates the first monitoring anomaly feature and the second monitoring anomaly feature of the cooling water pump, and through multi-index fusion and intelligent data analysis, while ensuring the safe operation of the power supply equipment in the computer room, effectively reduces energy consumption and maintenance risks. Description of the Drawings

[0014] Figure 1 It is a schematic diagram showing the change of the power change rate of the cooling water pump over time provided by an embodiment of the present invention; Figure 2 It is a two-dimensional floor plan of the refrigeration machine room system in the prior art energy management system provided by an embodiment of the present invention; Figure 3 It is a schematic diagram showing the change of the temperature change rate of the cooling water pump over time provided by an embodiment of the present invention; Figure 4 It is a schematic flowchart of a monitoring method for power-consuming equipment in a computer room provided by an embodiment of the present invention; Figure 5 It is a schematic flowchart of step 3 in a monitoring method for power-consuming equipment in a computer room provided by an embodiment of the present invention; Figure 6 It is a schematic flowchart of step 4 in a monitoring method for power-consuming equipment in a computer room provided by an embodiment of the present invention. Detailed implementation manners

[0015] Next, in combination with the accompanying drawings in the present invention, the technical solutions in the present invention will be clearly and completely described. Obviously, the described technical solutions are only a part of the present invention, rather than all of them. Based on the technical solutions in the present invention, all other technical solutions obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0016] Embodiment 1

[0017] In the embodiment of the present invention, there is provided a schematic flowchart of a monitoring method for power-consuming equipment in a computer room, and a monitoring method for power-consuming equipment in a computer room, including the following steps: Figure 1 as shown Step 1: Real-time collect and obtain the monitoring data of the cooling tower through the sensor network and the power factor detection module, and perform filtering, smoothing, and normalization processing on the monitoring data to obtain the first monitoring data. Construct a sliding time window to perform time window segmentation processing on the first monitoring data to obtain a monitoring sequence , where is the first monitoring data within the i-th time window is the number of time window segments , where is the j-th first monitoring data is the number of the first monitoring data in Step 2: Based on the first monitoring data, calculate the instantaneous power of the cooling water pump in real time to obtain the first power sequence within the same time window , where is the j-th instantaneous power is the m-th instantaneous power. Calculate the power change rate of the cooling water pump according to the first power sequence and obtain the power change rate sequence , where is the j-th power change rate is the (m - 1)-th power change rate. Calculate the power anomaly monitoring value within each time window through the power change rate sequence; the power anomaly monitoring value includes the mean value and the standard deviation Step 3: Extract the temperature data from the first monitoring data, calculate the temperature change rate within each time window according to the temperature data to generate a temperature change rate sequence, and calculate the first monitoring anomaly feature of the cooling water pump according to the temperature change rate sequence Step 4: Obtain the second monitoring anomaly feature of the cooling water pump according to the clustering distribution result between the power change rates within each time window Step 5: Obtain the first monitored abnormal feature and the second monitored abnormal feature, compare them with a preset abnormal threshold, and output an abnormal instruction according to the comparison result.

[0018] Figure 1 It is a schematic diagram showing the change of the power change rate of the cooling water pump over time provided by an embodiment of the present invention; the abscissa is time (from 0:00 to 12:00), the ordinate is the power change rate, and each data point on the curve represents the magnitude of the power change rate of the cooling water pump monitored at the corresponding time point, and the points are connected by a smooth curve.

[0019] Figure 3 It is a schematic diagram showing the change of the temperature change rate of the cooling water pump over time provided by an embodiment of the present invention; the abscissa of this figure is also time (from 0:00 to 12:00), and the ordinate is the temperature change rate. Each data point on the curve represents the magnitude of the temperature change rate of the cooling water pump monitored at the corresponding time point.

[0020] Specifically, in step 1, monitoring data is collected in real time through a sensor network and a power factor detection module. The sensor network includes a voltage sensor, a current sensor, and a temperature sensor. The voltage sensor is used to obtain the voltage data of the cooling water pump in real time, the current sensor is used to obtain the current data of the cooling water pump in real time, the temperature sensor is used to obtain the temperature data of the cooling water pump in real time, and the power factor detection module is used to monitor the power factor of the cooling water pump.

[0021] Specifically, in step 2, the instantaneous power of the cooling water pump is calculated in real time based on the first monitoring data. The calculation formula for the instantaneous power is; ; In the formula: is the instantaneous power at time t, is the voltage data at time t, is the current data at time t, is the power factor at time t; The jth power change rate is calculated by the formula: ; In the formula: is the jth instantaneous power, is the (j + 1)th instantaneous power, is the time interval between adjacent sampling points; Calculate the mean value and standard deviation within each time window through the power change rate sequence respectively. The specific formulas are: ; ; In the formula: is The mean value corresponding to the sequence, is the standard deviation corresponding to the sequence.

[0022] By collecting voltage, current, temperature, and power factor data in real time through a sensor network and using a high-frequency sliding time window for processing, it is possible to capture the dynamic changes in the device state within milliseconds and promptly detect abnormalities in the power and temperature of the cooling water pump. Calculate the instantaneous power, power change rate, and temperature change rate using the first monitoring data, and construct power anomaly monitoring values (mean, standard deviation) and temperature anomaly features respectively. Effectively combine electrical and thermal engineering indicators to identify abnormalities from multiple perspectives. The first monitoring anomaly feature extracts local temperature fluctuation information through the second-order difference of the temperature change rate. The second monitoring anomaly feature is based on the clustering distribution result of the power change rate, combined with statistical indicators (mean, standard deviation) and global frequency information, and can more accurately reflect local load changes and power fluctuation abnormalities. By comparing the monitoring anomaly features with preset thresholds, once an abnormal state is detected, an alarm command can be output. This can provide early warning and take measures before the cooling water pump causes abnormal temperature control in the computer room due to high load or insufficient heat dissipation, reducing the risk of system failures.

[0023] Specifically, Figure 4 is a schematic flow chart of step 3 in a monitoring method for electrical equipment in a computer room provided by an embodiment of the present invention; in step 3, calculating the first monitoring anomaly feature of the cooling water pump according to the temperature change rate sequence, the specific steps are as follows: Step 31, extract temperature data from the first monitoring data , calculate the temperature change rate within each time window according to the temperature data generate a temperature change rate sequence , is the k-th temperature change rate, is the number of temperature change rates within the time window; , is the (k + 1)-th temperature data within the time window, is the k-th temperature data within the time window, is the time interval between adjacent sampling points; Step 32, calculate the first monitoring anomaly feature of the cooling water pump according to the temperature change rate sequence, determine the temperature change rates of three consecutive sampling points within the time window, take the temperature change rate at the current moment minus twice the temperature change rate at the previous moment, and then add the temperature change rate at the previous moment as the numerator; Step 33, take the product of the reciprocal of the square of the time interval between adjacent sampling points and the numerator as the first monitoring anomaly feature .

[0024] The calculation formula for the first monitoring anomaly feature is: ; wherein: is the first monitoring abnormal feature, is the temperature change rate at time t, is the temperature change rate at time is the temperature change rate at time is the time interval between adjacent sampling points.

[0025] By calculating the temperature change rates of three consecutive sampling points, a quantitative index α 1 is constructed, which can accurately describe the amplitude and trend of local temperature fluctuations, facilitating comparison and judgment with a preset threshold; the second-order difference can reflect the acceleration of temperature change and is extremely sensitive to abnormal conditions such as temperature mutations, steep rises or falls, thereby enabling the early identification of potential equipment failures or heat dissipation abnormalities; after preprocessing such as filtering and smoothing, the features extracted using the second-order difference method can further reduce the false alarm risk caused by measurement noise or small fluctuations and improve the robustness of anomaly detection; based on the continuous calculation of sampling data, the value of α 1 can be updated in real time, thereby continuously monitoring the temperature dynamic changes of the cooling water pump and promptly detecting temperature control abnormalities caused by insufficient load or heat dissipation.

[0026] Specifically, Figure 5 is the flow schematic diagram of step 4 in a monitoring method for electrical equipment in a computer room provided by an embodiment of the present invention; in step 4, according to the clustering distribution result between the power change rates within each time window, the second monitoring abnormal feature of the cooling water pump is obtained, and the specific steps are as follows: Step 41, arrange the power change rate sequence composed of the power change rates within each time window in chronological order, and automatically divide the data in the power change rate sequence into several clustering clusters according to a clustering algorithm without presetting the number of clustering clusters; Step 42, for each data point in the power change rate sequence, use the fixed-length time period including this data point and centered on its time as the observation time window; Step 43, based on each data point in the power change rate sequence, construct a sliding time window with a fixed size centered on it, and calculate the second monitoring abnormal feature of the cooling water pump according to the distribution of elements within the observation time window of each power change rate and the distribution characteristics of the data within the clustering cluster.

[0027] Specifically, in step 43, calculating the second monitoring abnormal feature of the cooling water pump according to the distribution of elements within the observation time window of each power change rate and the distribution characteristics of the data within the clustering cluster, the specific steps are as follows: According to the obtained clustering results within each observation time window, count the number of different clustering clusters to which all power change rates belong within the observation time window, calculate the power anomaly monitoring value of the power change rate within the observation time window, calculate the difference between the mean and variance in the power anomaly monitoring value, and use the product of the number of clustering clusters and the difference as the numerator; For each power change rate within the observation time window, count its occurrence frequency in the entire power change rate sequence, and accumulate all frequencies to obtain the cumulative frequency of the data within the observation time window in the global difference sequence; Based on the numerator and the normalized product of the reciprocal of the cumulative frequency in the global difference sequence, it is used as the second monitoring anomaly feature of the cooling water pump.

[0028] The calculation formula for the second monitoring anomaly feature of the cooling water pump is: ; In the formula: is the second monitoring anomaly feature, is the mean value corresponding to the sequence, is the standard deviation corresponding to the sequence, is the number of clustering clusters, is the cumulative frequency in the difference sequence.

[0029] By counting the number of clustering clusters to which the power change rate belongs within the observation time window and calculating the statistical indicators within the window, α 2 can reflect the diversity and fluctuation of the local data distribution. Combining with the normalization of the cumulative frequency of the window data in the global difference sequence, the local anomaly feature can be combined with the overall data distribution, so as to more accurately identify the abnormal state; using a clustering algorithm without presetting the number of clustering clusters enables the method to adapt to the diversity and complexity of data under different working conditions and avoid the deviation introduced by artificially setting the number of clusters; when there are diverse and abnormal change patterns in the power change rate within the local window, the number of clustering clusters will increase, and at the same time, the change in the difference between the mean and the standard deviation will also reflect the instability of the data, thereby making α 2 value increase significantly; by fusing the local distribution feature and the global data occurrence frequency, it can effectively distinguish normal fluctuations from abnormal changes, thus improving the detection accuracy and response speed of the abnormal state of the cooling water pump power.

[0030] During the monitoring process of the cooling water pump in the computer room, the sensor network collects the following data in real time: Each sampling point records the voltage U (unit: V), current I (unit: A), power factor cosφ, and temperature T (unit: °C). For example, the data within the time range of 0 to 5 seconds is as follows: Time 0 s: U = 230 V, I = 10.0 A, cosφ = 0.95, T = 35.0 °C; Time 1 s: U = 231 V, I = 10.2 A, cosφ = 0.95, T = 35.2 °C; Time 2 s: U = 232 V, I = 10.1 A, cosφ = 0.96, T = 35.5 °C; Time 3 s: U = 233 V, I = 10.3 A, cosφ = 0.94, T = 35.8 °C; Time 4 s: U = 230 V, I = 10.2 A, cosφ = 0.95, T = 36.0 °C; Time 5 s: U = 229 V, I = 10.0 A, cosφ = 0.96, T = 36.2 °C.

[0031] Calculation of instantaneous power and power change rate: Calculate the instantaneous power at each moment using the formula: Time 0: P0 = 230 × 10.0 × 0.95 ≈ 2185 W; Time 1: P1 ≈ 2238 W; Time 2: P2 ≈ 2250 W; Time 3: P3 ≈ 2256 W; Time 4: P4 ≈ 2233 W; Time 5: P5 ≈ 2198 W; Subsequently, calculate the power change rate between adjacent sampling points: Obtained: ΔP0 = P1 - P0 = 2238 - 2185 = +53 W; ΔP1 = P2 - P1 = 2250 - 2238 = +12 W; ΔP2 = P3 - P2 = 2256 - 2250 = +6 W; ΔP3 = P4 - P3 = 2233 - 2256 = -23 W; ΔP4 = P5 - P4 = 2198 - 2233 = -35 W; Calculate the mean and standard deviation of the power change rate within this window: ; ; Calculation of temperature change rate and first monitoring anomaly characteristics: Calculate the temperature change rate from the temperature data: Time 0 - 1: 0.2 °C; Time 1 - 2: 0.3 °C; Time 2 - 3: 0.3 °C; Time 3 - 4: 0.2 °C; Time 4 - 5: 0.2 °C; For example, at time 3 seconds: ; Similarly, the values calculated at subsequent moments are all around an absolute value of 0.1.

[0032] Specifically, in step 5, the first monitoring abnormal feature and the second monitoring abnormal feature are obtained and compared with a preset abnormal threshold, and an abnormal existence instruction is output according to the comparison result. Specifically: The first monitoring abnormal feature is compared with a preset first abnormal threshold. If the first monitoring abnormal feature is greater than or equal to the preset first abnormal threshold, an abnormal existence instruction is output; if the first monitoring abnormal feature is less than the preset first abnormal threshold, no output is made; The second monitoring abnormal feature is compared with a preset second abnormal threshold. If the second monitoring abnormal feature is greater than or equal to the preset second abnormal threshold, an abnormal existence instruction is output; if the second monitoring abnormal feature is less than the preset second abnormal threshold, no output is made.

[0033] In the embodiment of the present invention, the monitoring data of the cooling tower is collected and obtained in real time through a sensor network and a power factor detection module, and a sliding time window is constructed to perform time window segmentation processing on the first monitoring data to obtain a monitoring sequence; the instantaneous power of the cooling water pump is calculated in real time based on the first monitoring data to obtain a first power sequence within the same time window, the power change rate of the cooling water pump is calculated according to the first power sequence and a power change rate sequence is obtained, the power abnormal monitoring value within each time window is calculated through the power change rate sequence, the first monitoring abnormal feature and the second monitoring abnormal feature of the cooling water pump are analyzed and calculated, and through multi - index fusion and intelligent data analysis, while ensuring the safe operation of the power supply equipment in the computer room, the energy consumption and maintenance risks are effectively reduced.

[0034] Embodiment 2

[0035] A monitoring device for electrical equipment in a computer room, including a data acquisition module, a data processing module, a first monitoring abnormal analysis module, a second monitoring abnormal analysis module, and an alarm and control module; the data acquisition module is connected to the data processing module, the data processing module is respectively connected to the first monitoring abnormal analysis module and the second monitoring abnormal analysis module, and the first monitoring abnormal analysis module and the second monitoring abnormal analysis module are respectively connected to the alarm and control module; The data acquisition module is used to collect the monitoring data of the cooling tower in real time through the sensor network and the power factor detection module, and perform filtering, smoothing, and normalization processing on the monitoring data to obtain the first monitoring data. A sliding time window is constructed to perform time window segmentation processing on the first monitoring data to obtain a monitoring sequence; The data processing module is used to calculate the instantaneous power of the cooling water pump in real time based on the first monitoring data to obtain the first power sequence within the same time window, calculate the power change rate of the cooling water pump according to the first power sequence, and obtain the power change rate sequence, and calculate the power anomaly monitoring value within each time window through the power change rate sequence; The first monitoring anomaly analysis module is used to extract temperature data from the first monitoring data, calculate the temperature change rate within each time window according to the temperature data to generate a temperature change rate sequence, and calculate the first monitoring anomaly feature of the cooling water pump according to the temperature change rate sequence; The second monitoring anomaly analysis module obtains the second monitoring anomaly feature of the cooling water pump according to the clustering distribution result between the power change rates within each time window; The alarm and control module is used to obtain the first monitoring anomaly feature and the second monitoring anomaly feature and compare them with the preset anomaly threshold, and output an anomaly instruction according to the comparison result.

[0036] Embodiment 3

[0037] Based on the same inventive concept, an embodiment of the present invention provides an electronic device, including: a processor; a memory; and a computer program; wherein, the computer program is stored in the memory and is configured to be executed by the processor to implement the monitoring method for the electrical equipment in the computer room provided as described above. The method includes: collecting the monitoring data of the cooling tower in real time through the sensor network and the power factor detection module, and performing filtering, smoothing, and normalization processing on the monitoring data to obtain the first monitoring data, and constructing a sliding time window to perform time window segmentation processing on the first monitoring data to obtain a monitoring sequence ; calculating the instantaneous power of the cooling water pump in real time based on the first monitoring data to obtain the first power sequence within the same time window , calculating the power change rate of the cooling water pump according to the first power sequence and obtaining the power change rate sequence , calculate the power anomaly monitoring values within each time window through the power change rate sequence; the power anomaly monitoring values include the mean value and the standard deviation; extract the temperature data from the first monitoring data, calculate the temperature change rate within each time window according to the temperature data to generate a temperature change rate sequence, and calculate the first monitoring anomaly feature of the cooling water pump according to the temperature change rate sequence; obtain the second monitoring anomaly feature of the cooling water pump according to the clustering distribution result among the power change rates within each time window; obtain the first monitoring anomaly feature and the second monitoring anomaly feature and compare them with a preset anomaly threshold, and output an anomaly instruction according to the comparison result.

[0038] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other deformations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be regarded as consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A monitoring method for electrical equipment in a computer room, characterized in that: The steps include: Step 1: collect and obtain the monitoring data of the cooling tower in real time through the sensor network and the power factor detection module, and filter, smooth and normalize the monitoring data to obtain the first monitoring data, construct a sliding time window, and perform time window segmentation processing on the first monitoring data to obtain the monitoring sequence ; Step 2: Calculate the instantaneous power of the cooling water pump in real time based on the first monitoring data to obtain the first power sequence in the same time window. , calculate the power change rate of the cooling water pump according to the first power sequence and obtain the power change rate sequence , the power abnormality monitoring value in each time window is calculated respectively through the power change rate sequence; the power abnormality monitoring value includes the mean and the standard deviation; Step 3, extracting temperature data from the first monitoring data, calculating the temperature change rate in each time window according to the temperature data to generate a temperature change rate sequence, and calculating the first monitoring abnormality feature of the cooling water pump according to the temperature change rate sequence; Step 4, obtaining a second monitoring abnormal feature of the cooling water pump according to the cluster distribution result between the power change rates in each time window; Step 5: Obtain the first monitoring abnormality feature and the second monitoring abnormality feature and compare them with a preset abnormality threshold, and output an abnormality indication according to the comparison result.

2. A method for monitoring electrical equipment in a computer room as claimed in claim 1, characterized in that: In step 1, monitoring data is collected in real time through a sensor network and a power factor detection module. The sensor network includes a voltage sensor, a current sensor, and a temperature sensor. The voltage data of the cooling water pump is obtained in real time through the voltage sensor, the current data of the cooling water pump is obtained in real time through the current sensor, and the temperature data of the cooling water pump is obtained in real time through the temperature sensor. The power factor detection module is used to monitor the power factor of the cooling water pump.

3. A method for monitoring electrical equipment in a computer room as claimed in claim 1, characterized in that: In step 3, the first monitoring abnormality feature of the cooling water pump is calculated according to the temperature change rate sequence. The specific steps are: Step 31, extracting temperature data from the first monitoring data , calculate the temperature change rate in each time window based on the temperature data Generate a temperature rate of change series ; Step 32, calculating the first monitoring abnormality feature of the cooling water pump according to the temperature change rate sequence, determining the temperature change rate of three consecutive sampling points in the time window, taking the temperature change rate at the current moment minus twice the temperature change rate at the previous moment, and adding the temperature change rate at the previous moment as the numerator; Step 33: The product of the reciprocal of the square of the time interval between adjacent sampling points and the numerator is used as the first monitoring abnormality feature. .

4. A method for monitoring electrical equipment in a computer room as claimed in claim 1, characterized in that: In step 4, the second monitoring abnormality feature of the cooling water pump is obtained according to the cluster distribution result between the power change rates in each time window. The specific steps are: Step 41, arranging the power change rate sequence composed of the power change rate in each time window in chronological order, and automatically dividing the data in the power change rate sequence into a plurality of clusters according to a clustering algorithm without presetting the number of clusters; Step 42, for each data point in the power change rate sequence, a fixed-length time period including the data point and centered at the time at which the data point is located is used as an observation time window; Step 43, based on each data point in the power change rate sequence, a sliding time window of fixed size is constructed with it as the center point, and the second monitoring abnormality feature of the cooling water pump is calculated based on the distribution of elements in the observation time window of each power change rate and the distribution characteristics of the data in the cluster.

5. A method for monitoring electrical equipment in a computer room as claimed in claim 4, characterized in that: In step 43, the second monitoring abnormality feature of the cooling water pump is calculated based on the distribution of elements in the observation time window of each power change rate and the distribution characteristics of the data in the cluster. The specific steps are: In each observation time window, according to the obtained clustering results, the number of different clusters to which all power change rates in the observation time window belong is counted, the power abnormality monitoring value of the power change rate in the observation time window is calculated, the difference between the mean and the variance of the power abnormality monitoring value is calculated, and the product of the number of clusters and the difference is used as the numerator; For each power change rate within the observation time window, count its frequency of occurrence in the entire power change rate sequence, and accumulate all frequencies to obtain the cumulative frequency of the data within the observation time window in the global difference sequence; The normalized product of the numerator and the inverse of the accumulated frequency in the global difference sequence is used as the second monitoring abnormal feature of the cooling water pump.

6. A monitoring device for electrical equipment in a computer room, comprising a data acquisition module, a data processing module, a first monitoring abnormality analysis module, a second monitoring abnormality analysis module, and an alarm and control module, characterized in that: The data acquisition module is used to acquire the monitoring data of the cooling tower in real time through the sensor network and the power factor detection module, and to filter, smooth and normalize the monitoring data to obtain the first monitoring data, and to construct a sliding time window to perform time window segmentation processing on the first monitoring data to obtain a monitoring sequence; The data processing module is used to calculate the instantaneous power of the cooling water pump in real time based on the first monitoring data to obtain the first power sequence in the same time window, calculate the power change rate of the cooling water pump according to the first power sequence and obtain the power change rate sequence, and calculate the power abnormality monitoring value in each time window respectively through the power change rate sequence; The first monitoring abnormality analysis module is used to extract temperature data from the first monitoring data, calculate the temperature change rate in each time window according to the temperature data to generate a temperature change rate sequence, and calculate the first monitoring abnormality feature of the cooling water pump according to the temperature change rate sequence; The second monitoring abnormality analysis module obtains the second monitoring abnormality feature of the cooling water pump according to the cluster distribution result between the power change rates in each time window; The alarm and control module is used to obtain the first monitoring abnormality feature and the second monitoring abnormality feature, compare them with the preset abnormality threshold, and output an abnormality instruction according to the comparison result.

7. An electronic device, characterized in that: include: Memory; Processor; And a computer program; wherein the computer program is stored in the memory and is configured to be executed by the processor to implement the monitoring method for electrical equipment in a computer room as described in any one of claims 1 to 5.

Images