CN112948230A - Data processing method and device based on machine room confidential air conditioner - Google Patents

Data processing method and device based on machine room confidential air conditioner Download PDF

Info

Publication number
CN112948230A
CN112948230A CN202110345461.2A CN202110345461A CN112948230A CN 112948230 A CN112948230 A CN 112948230A CN 202110345461 A CN202110345461 A CN 202110345461A CN 112948230 A CN112948230 A CN 112948230A
Authority
CN
China
Prior art keywords
data
detected
historical
target
sampling number
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110345461.2A
Other languages
Chinese (zh)
Inventor
何城
徐志轩
董亮
习正
刘欢
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Construction Bank Corp
Original Assignee
China Construction Bank Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Construction Bank Corp filed Critical China Construction Bank Corp
Priority to CN202110345461.2A priority Critical patent/CN112948230A/en
Publication of CN112948230A publication Critical patent/CN112948230A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3409—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for performance assessment
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/32—Monitoring with visual or acoustical indication of the functioning of the machine
    • G06F11/324—Display of status information
    • G06F11/327—Alarm or error message display
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Quality & Reliability (AREA)
  • Computer Hardware Design (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

The invention discloses a data processing method and device based on a machine room confidential air conditioner, and relates to the technical field of data analysis. One embodiment of the method comprises: receiving a data processing request, and acquiring data to be detected of the machine room precision air conditioner according to the data processing request, wherein the data to be detected comprises: measuring the temperature to be detected and the humidity to be detected; analyzing the data to be detected based on a brink analysis algorithm, and determining upper and lower limit thresholds corresponding to the data to be detected; and if the data to be detected is out of the upper and lower limit threshold range corresponding to the data to be detected, identifying the data to be detected as abnormal data, and alarming the abnormal data. This embodiment has promoted the accuracy of testing result, has reduced the wrong report rate of police of the accurate air conditioner of computer lab, has avoided the waste of a large amount of manpowers to adopt the brink analysis algorithm, can accelerate computational rate, further improve and detect the precision.

Description

Data processing method and device based on machine room confidential air conditioner
Technical Field
The invention relates to the technical field of data analysis, in particular to a data processing method and device based on a machine room confidential air conditioner.
Background
The machine room precision air conditioner is a special air conditioner designed for a modern electronic equipment machine room. When computers, program controlled switches and other equipment are placed in a machine room, the temperature and humidity of the machine room environment need to be strictly controlled within a specific range in order to improve the stability and reliability of the use of the equipment in the machine room. If the equipment in the machine room breaks down or the precise air conditioner in the machine room breaks down, the temperature and humidity in the machine room are suddenly high and suddenly low, and the equipment is easily damaged. Therefore, it is important for the precision air conditioner in the machine room to detect the abnormal values of the temperature and the humidity in real time.
At present, a fixed threshold value of temperature and humidity is mainly set for a precision air conditioner of a machine room, and the temperature and humidity exceeding the fixed threshold value is alarmed. However, because of a lot of interference factors in the machine room environment, the existing method for setting the fixed threshold value can cause inaccurate detection results and high false alarm rate. Moreover, currently, a large amount of manpower can be wasted by setting a fixed threshold value of the temperature and the humidity mostly through a manual observation mode.
Disclosure of Invention
In view of this, embodiments of the present invention provide a data processing method and apparatus based on a machine room confidential air conditioner, which can improve accuracy of a detection result, reduce false alarm rate of the machine room precise air conditioner, avoid waste of a large amount of manpower, and can accelerate a calculation speed and further improve detection precision by using a brink analysis algorithm.
To achieve the above object, according to an aspect of an embodiment of the present invention, a data processing method based on a machine room confidential air conditioner is provided.
The data processing method based on the machine room confidential air conditioner comprises the following steps: receiving a data processing request, and acquiring data to be detected of the precision air conditioner of the machine room according to the data processing request, wherein the data to be detected comprises: measuring the temperature to be detected and the humidity to be detected; analyzing the data to be detected based on a brink analysis algorithm, and determining upper and lower limit thresholds corresponding to the data to be detected; and if the data to be detected is out of the upper and lower limit threshold range corresponding to the data to be detected, identifying the data to be detected as abnormal data, and alarming the abnormal data.
Optionally, the analyzing the data to be detected based on the brink analysis algorithm to determine the upper and lower limit thresholds corresponding to the data to be detected includes: acquiring sampling data corresponding to the data to be detected according to the target sampling number of a moving average method, wherein the sampling data corresponding to the data to be detected is data before the data to be detected; calculating a mean value and a standard deviation corresponding to the data to be detected according to the target sampling number, the data to be detected and sampling data corresponding to the data to be detected; and substituting the standard deviation factor, the mean value and the standard deviation corresponding to the data to be detected into an upper limit threshold value calculation formula and a lower limit threshold value calculation formula, and calculating the upper limit threshold value and the lower limit threshold value corresponding to the data to be detected.
Optionally, the target number of samples is determined according to the following process: setting an initial sampling number of a moving average method, and acquiring historical data of the precise air conditioner of the machine room; calculating a mean value corresponding to the historical data according to the initial sampling number; performing differentiation calculation on the historical data and the average value corresponding to the historical data to obtain a differentiation value corresponding to the initial sampling number; and adjusting the initial sampling number for preset times according to the differential value corresponding to the initial sampling number, and determining the target sampling number according to an adjustment result.
Optionally, the calculating a mean value corresponding to the historical data according to the initial number of samples includes: and acquiring sampling data corresponding to the historical data according to the initial sampling number, and then calculating a mean value corresponding to the historical data according to the initial sampling number, the historical data and the sampling data corresponding to the historical data, wherein the sampling data corresponding to the historical data is data before the historical data.
Optionally, the adjusting the initial sampling number by a preset number of times and determining the target sampling number according to an adjustment result includes: adjusting the initial sampling number for preset times, and calculating a differential value corresponding to the sampling number after each adjustment to obtain differential values corresponding to all the sampling numbers; and selecting the minimum differentiation value from the differentiation values corresponding to all the sampling numbers, and determining the sampling number corresponding to the minimum differentiation value as the target sampling number.
Optionally, after calculating the difference value corresponding to each adjusted sampling number, the method further includes: judging whether the calculated differentiation value is smaller than a preset differentiation threshold value or not; if so, finishing the adjustment, and determining the sampling number corresponding to the calculated differentiation value as the target sampling number.
Optionally, before obtaining the sample data corresponding to the historical data according to the initial number of samples, the method further includes: judging whether the difference value between the data quantity before the historical data and the initial sampling quantity is smaller than-1; if yes, calculating a mean value corresponding to the historical data according to the data quantity, the previous data of the historical data and the historical data; if not, acquiring sampling data corresponding to the historical data according to the initial sampling number, and then calculating a mean value corresponding to the historical data.
Optionally, the method further comprises: and adjusting the initial sampling number based on a machine learning algorithm.
Optionally, after determining that the number of samples corresponding to the minimum differentiation value is the target number of samples, the method further includes: determining a target mean value and a target standard deviation corresponding to the historical data according to the target sampling number; and calculating an upper threshold and a lower threshold corresponding to the historical data according to the historical data and the target standard deviation corresponding to the historical data and by combining standard deviation factors.
Optionally, the target mean is a mean corresponding to the historical data calculated according to the target sampling number, and the target standard deviation is a standard deviation corresponding to the historical data calculated according to the target sampling number.
Optionally, the method further comprises: and taking an X axis as the time of the historical data, and taking a Y axis as a target mean value corresponding to the historical data, an upper threshold value and a lower threshold value corresponding to the historical data, and generating a mean value line, an upper base line and a lower base line corresponding to the historical data so as to be displayed by using a graph.
Optionally, if the data to be detected is outside the upper and lower limit threshold range corresponding to the data to be detected, identifying the data to be detected as abnormal data, and giving an alarm to the abnormal data, includes: if the data to be detected is larger than the upper threshold value or the data to be detected is smaller than the lower threshold value, identifying the data to be detected as abnormal data; and inquiring the machine room precision air conditioner to which the abnormal data belongs, and acquiring the contact way of the alarm person of the machine room precision air conditioner to which the abnormal data belongs so as to send alarm information.
Optionally, the method further comprises: and generating a mean line, an upper base line and a lower base line corresponding to the data to be detected by taking an X axis as the time of the data to be detected and taking a Y axis as a mean value corresponding to the data to be detected and an upper threshold value and a lower threshold value corresponding to the data to be detected so as to display by using a graph.
To achieve the above object, according to still another aspect of an embodiment of the present invention, there is provided a data processing apparatus for a machine room confidential air conditioner.
The data processing device based on the machine room confidential air conditioner comprises the following components: the acquisition module is used for receiving a data processing request and acquiring data to be detected of the precision air conditioner of the machine room according to the data processing request, wherein the data to be detected comprises: measuring the temperature to be detected and the humidity to be detected; the determining module is used for analyzing the data to be detected based on a brink analysis algorithm and determining upper and lower limit thresholds corresponding to the data to be detected; and the alarm module is used for identifying the data to be detected as abnormal data and giving an alarm to the abnormal data if the data to be detected is out of the upper and lower limit threshold range corresponding to the data to be detected.
Optionally, the determining module is further configured to: acquiring sampling data corresponding to the data to be detected according to the target sampling number of a moving average method, wherein the sampling data corresponding to the data to be detected is data before the data to be detected; calculating a mean value and a standard deviation corresponding to the data to be detected according to the target sampling number, the data to be detected and sampling data corresponding to the data to be detected; and substituting the standard deviation factor, the mean value and the standard deviation corresponding to the data to be detected into an upper limit threshold value calculation formula and a lower limit threshold value calculation formula, and calculating the upper limit threshold value and the lower limit threshold value corresponding to the data to be detected.
Optionally, the apparatus further comprises an algorithm training module, configured to determine the target number of samples according to the following process: setting an initial sampling number of a moving average method, and acquiring historical data of the precise air conditioner of the machine room; calculating a mean value corresponding to the historical data according to the initial sampling number; performing differentiation calculation on the historical data and the average value corresponding to the historical data to obtain a differentiation value corresponding to the initial sampling number; and adjusting the initial sampling number for preset times according to the differential value corresponding to the initial sampling number, and determining the target sampling number according to an adjustment result.
Optionally, the algorithm training module is further configured to: and acquiring sampling data corresponding to the historical data according to the initial sampling number, and then calculating a mean value corresponding to the historical data according to the initial sampling number, the historical data and the sampling data corresponding to the historical data, wherein the sampling data corresponding to the historical data is data before the historical data.
Optionally, the algorithm training module is further configured to: adjusting the initial sampling number for preset times, and calculating a differential value corresponding to the sampling number after each adjustment to obtain differential values corresponding to all the sampling numbers; and selecting the minimum differentiation value from the differentiation values corresponding to all the sampling numbers, and determining the sampling number corresponding to the minimum differentiation value as the target sampling number.
Optionally, the algorithm training module is further configured to: judging whether the calculated differentiation value is smaller than a preset differentiation threshold value or not; if so, finishing the adjustment, and determining the sampling number corresponding to the calculated differentiation value as the target sampling number.
Optionally, the algorithm training module is further configured to: judging whether the difference value between the data quantity before the historical data and the initial sampling quantity is smaller than-1; if yes, calculating a mean value corresponding to the historical data according to the data quantity, the previous data of the historical data and the historical data; if not, acquiring sampling data corresponding to the historical data according to the initial sampling number, and then calculating a mean value corresponding to the historical data.
Optionally, the algorithm training module is further configured to: and adjusting the initial sampling number based on a machine learning algorithm.
Optionally, the algorithm training module is further configured to: determining a target mean value and a target standard deviation corresponding to the historical data according to the target sampling number, wherein the target mean value is a mean value corresponding to the historical data calculated according to the target sampling number, and the target standard deviation is a standard deviation corresponding to the historical data calculated according to the target sampling number; and calculating an upper threshold and a lower threshold corresponding to the historical data according to the historical data and the target standard deviation corresponding to the historical data and by combining standard deviation factors.
Optionally, the apparatus further comprises a display module for: and taking an X axis as the time of the historical data, and taking a Y axis as a target mean value corresponding to the historical data, an upper threshold value and a lower threshold value corresponding to the historical data, and generating a mean value line, an upper base line and a lower base line corresponding to the historical data so as to be displayed by using a graph.
Optionally, the alarm module is further configured to: if the data to be detected is larger than the upper threshold value or the data to be detected is smaller than the lower threshold value, identifying the data to be detected as abnormal data; and inquiring the machine room precision air conditioner to which the abnormal data belongs, and acquiring the contact way of the alarm person of the machine room precision air conditioner to which the abnormal data belongs so as to send alarm information.
Optionally, the display module is further configured to: and generating a mean line, an upper base line and a lower base line corresponding to the data to be detected by taking an X axis as the time of the data to be detected and taking a Y axis as a mean value corresponding to the data to be detected and an upper threshold value and a lower threshold value corresponding to the data to be detected so as to display by using a graph.
To achieve the above object, according to still another aspect of an embodiment of the present invention, there is provided an electronic apparatus.
An electronic device of an embodiment of the present invention includes: one or more processors; and the storage device is used for storing one or more programs, and when the one or more programs are executed by one or more processors, the one or more processors realize the data processing method based on the confidential air conditioner of the machine room.
To achieve the above object, according to still another aspect of an embodiment of the present invention, there is provided a computer-readable medium.
A computer-readable medium of an embodiment of the present invention has a computer program stored thereon, and the program, when executed by a processor, implements a data processing method of a machine room secret-based air conditioner of an embodiment of the present invention.
One embodiment of the above invention has the following advantages or benefits: treat the detection temperature based on brink analysis algorithm, treat that it analyzes to detect humidity, confirm to treat the detection temperature, treat the upper and lower limit threshold value that the humidity corresponds, and then can combine the upper and lower limit threshold value of confirming, judge whether it is unusual data to treat the data, can set up different threshold values for the different humiture that treats, the problem that the detection result that prior art set up fixed threshold value and bring is inaccurate and the false alarm rate is high is solved, the accuracy of detection result has been promoted, the false alarm rate of the accurate air conditioner of computer lab has been reduced, the waste of a large amount of manpowers has been avoided, and adopt brink analysis algorithm, can accelerate the computational rate, further improve the detection precision.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
fig. 1 is a schematic diagram of main steps of a data processing method based on a machine room confidential air conditioner according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of the main process of determining a target number of samples according to an embodiment of the invention;
fig. 3 is a schematic diagram of a main process of a data processing method based on a machine room confidential air conditioner according to an embodiment of the present invention;
fig. 4 is a schematic diagram of main modules of a data processing apparatus based on a machine room confidential air conditioner according to an embodiment of the present invention;
FIG. 5 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 6 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic diagram of main steps of a data processing method based on a machine room confidential air conditioner according to an embodiment of the present invention. As shown in fig. 1, the data processing method based on the confidential air conditioner in the machine room may include the following main steps:
step S101, receiving a data processing request, and acquiring to-be-detected data of the precision air conditioner in the machine room according to the data processing request;
step S102, analyzing data to be detected based on a brink analysis algorithm, and determining upper and lower limit thresholds corresponding to the data to be detected;
and S103, if the data to be detected is out of the upper and lower limit threshold range corresponding to the data to be detected, identifying the data to be detected as abnormal data, and alarming the abnormal data.
The data processing request refers to a request for detecting data of the precision air conditioner in the machine room. For example, the background system acquires data of the precise air conditioner of the machine room once every 5 minutes, and the acquired data needs to be detected; for another example, a request for detecting air conditioning data is generated according to actual requirements. After the data processing request is received, the data to be detected of the precision air conditioner in the machine room can be obtained according to the data processing request. In the embodiment of the invention, the data to be detected can be the temperature of the air conditioner and can also be the humidity of the air conditioner.
After the data to be detected is obtained, in step S102, the data to be detected may be analyzed based on a brink analysis algorithm, so as to obtain an upper and lower limit threshold corresponding to the data to be detected. Among them, brin band is also called as force retention plus channel, boningjie band or brazier plus channel, and is a technical analysis tool. The brinell band analysis algorithm combines the moving average method and the standard deviation concept, and the basic pattern is a band channel consisting of three track lines.
As an embodiment of the present invention, analyzing data to be detected based on a brink analysis algorithm, and determining upper and lower limit thresholds corresponding to the data to be detected may include:
(1) and acquiring sampling data corresponding to the data to be detected according to the target sampling number of the moving average method.
The moving average method is a simple smooth prediction technology, and the basic idea is as follows: and calculating the time-sequence average value containing a certain number of terms in sequence according to the time-sequence data item by item in order to reflect the long-term trend. Therefore, when the numerical value of the time series is influenced by the periodic variation and the random fluctuation, the fluctuation is large, and the development trend of the event is not easy to display, the influence of the factors can be eliminated by using a moving average method, the development direction and the development trend of the event are displayed, and then the long-term trend of the time series is analyzed and predicted according to the trend line. The moving average is calculated as follows: ft＝(At-1+At-2+At-3+…+At-n) And/n. In the formula, FtDenotes the predicted value for the next epoch, n denotes the number of terms of the moving average method, At-1Representing the previous actual value, At-2、At-3And At-nThe actual values of the first 2 nd, 3 rd and n th stages are shown.
In the data processing method based on the machine room confidential air conditioner according to the embodiment of the invention, the target sampling number of the moving average method is equivalent to the item number of the moving average method, and for convenience of description, the target sampling number of the moving average method is represented by N. In the process of calculating the mean value corresponding to the data to be detected, the sampling data corresponding to the data to be detected needs to be acquired, that is, the mean value calculation is performed by using the data before the data to be detected. In addition, the data to be detected can be combined when the mean value corresponding to the data to be detected is calculated, so that the sampling data corresponding to the data to be detected is (N-1) data before the data to be detected. In the embodiment of the invention, the data of the machine room precision air conditioner is collected at regular time, the collected data is stored in the data information table of the machine room precision air conditioner, and the collection time corresponding to each data is stored in the data information table. Obviously, the data information table stores ordered air conditioner data, so that (N-1) data before the data to be detected can be acquired from the data information table. In addition, the target sampling number is obtained through historical data, and in order to improve the accuracy of the detection result of the technical scheme, the target sampling number is obtained through analysis by combining a large amount of historical data. Therefore, a large amount of historical data exists before the data to be detected, namely, the number of data before the data to be detected is considered to be more than (N-1).
(2) And calculating the mean value and the standard deviation corresponding to the data to be detected according to the target sampling number, the data to be detected and the sampling data corresponding to the data to be detected.
And the average value corresponding to the data to be detected is (the data to be detected + the sampling data corresponding to the data to be detected)/the target sampling number. Correspondingly, the mean value corresponding to the sampling data can be calculated, and then the standard deviation corresponding to the data to be detected is calculated according to the difference value between the data to be detected and the mean value corresponding to the data to be detected, the difference value between the sampling data and the mean value corresponding to the sampling data and the target sampling number.
(3) And substituting the standard deviation factor, the mean value and the standard deviation corresponding to the data to be detected into an upper limit threshold value calculation formula and a lower limit threshold value calculation formula, and calculating the upper limit threshold value and the lower limit threshold value corresponding to the data to be detected.
The upper and lower limit threshold calculation formula comprises: an upper threshold calculation formula and a lower threshold calculation formula. The upper threshold calculation formula is:
Figure BDA0003000665380000091
the lower threshold calculation formula is:
Figure BDA0003000665380000092
in the formula, Z is the data to be detected,
Figure BDA0003000665380000093
is the corresponding mean value, sigma, of the data Z to be detectedZIs the standard deviation corresponding to the data Z to be detected, ZUPIs the upper threshold value corresponding to the data Z to be detected, ZLOWThe lower threshold corresponding to the data to be detected, and beta is a standard deviation factor.
The standard deviation factor β is generally set to 1, 2, and 4. By setting different beta values, the data of the precise air conditioner in the machine room can be evaluated. Data in the range of beta being 1 is excellent, temperature value in the range of beta being 2 is good, data in the range of beta being 4 is general, data beyond the range of beta being 4 is serious, and alarm information needs to be sent.
In addition, the target sampling number of the corresponding moving average method is different for different data to be detected. If the data to be detected is the current temperature of the precise air conditioner of a certain machine room, calculating the mean value and the standard deviation corresponding to the current temperature according to the target sampling number corresponding to the temperature, and finally determining the upper limit threshold and the lower limit threshold corresponding to the current temperature so as to judge whether the current temperature is abnormal; if the data to be detected is the current humidity of the precision air conditioner in a certain machine room, then the average value and the standard deviation corresponding to the current humidity can be calculated according to the target sampling number corresponding to the humidity, and finally the upper limit threshold and the lower limit threshold corresponding to the current humidity are determined, so that whether the current humidity is abnormal or not can be judged.
It should be noted that there may be one or more data to be detected, and in the embodiment of the present invention, each data to be detected may be analyzed to determine whether the data to be detected is abnormal. For example, the data to be detected are temperatures of multiple machine room precision air conditioners and humidities of multiple machine room precision air conditioners, and each temperature or each humidity needs to be analyzed to determine whether the temperature or the humidity is abnormal.
As an embodiment of the present invention, if the data to be detected is outside the upper and lower threshold ranges corresponding to the data to be detected, the step S103 identifies the data to be detected as abnormal data, and alarms the abnormal data, which may include: if the data to be detected is larger than the upper limit threshold value or the data to be detected is smaller than the lower limit threshold value, identifying the data to be detected as abnormal data; and inquiring the machine room precision air conditioner to which the abnormal data belongs, and acquiring the contact way of the alarm person of the machine room precision air conditioner to which the abnormal data belongs so as to send alarm information. For example, Z is the data to be detected, ZUPIs the upper threshold value corresponding to the data Z to be detected, ZLOWAnd the lower threshold value is corresponding to the data to be detected. If the data Z to be detected is larger than the upper limit threshold value ZUPOr Z is less than the lower threshold ZLOWIf the Z is determined to be abnormal data, the data of which machine room precision air conditioner the Z is required to be inquired, the contact way of the responsible person of the air conditioner, namely the contact way of the alarm person, is obtained, and then the alarm information can be sent to the responsible person.
In the prior art, the fixed threshold value of the temperature and the humidity is set for the precise air conditioner of the machine room, so that the detection result is inaccurate, and the false alarm rate is high. Moreover, currently, a large amount of manpower can be wasted by setting a fixed threshold value of the temperature and the humidity mostly through a manual observation mode. However, in the data processing method based on the machine room confidential air conditioner according to the embodiment of the present invention, the temperature to be detected and the humidity to be detected can be analyzed based on the brink analysis algorithm, the upper and lower threshold values corresponding to the temperature to be detected and the humidity to be detected are determined, and then the determined upper and lower threshold values can be combined to determine whether the data to be detected is abnormal data, and different threshold values can be set for different temperatures and humidities to be detected, so that the problems of inaccurate detection result and high false alarm rate caused by setting a fixed threshold value in the prior art are solved, the accuracy of the detection result is improved, the false alarm rate of the machine room confidential air conditioner is reduced, and a large amount of manpower waste is avoided.
In the data processing method based on the machine room confidential air conditioner, the target sampling number N of the moving average method is equivalent to the number of terms of the moving average method, and the mean value, the standard deviation and the upper and lower limit thresholds corresponding to the data to be detected can be calculated according to the target sampling number N, so that the selection of the target sampling number N has important significance. Fig. 2 is a schematic diagram of a main process of determining a target number of samples according to an embodiment of the present invention. As shown in fig. 2, the main process of determining the target sampling number may include:
step S201, setting an initial sampling number of a moving average method, and acquiring historical data of the precision air conditioner of the machine room;
step S202, acquiring sampling data corresponding to historical data according to the initial sampling number, and then calculating an average value corresponding to the historical data according to the initial sampling number, the historical data and the sampling data corresponding to the historical data, wherein the sampling data corresponding to the historical data is data before the historical data;
step S203, performing differentiation calculation on the historical data and the average value corresponding to the historical data to obtain a differentiation value corresponding to the initial sampling number;
step S204, adjusting the initial sampling number for preset times according to the difference value corresponding to the initial sampling number, and calculating the difference value corresponding to the sampling number after each adjustment to obtain the difference values corresponding to all the sampling numbers;
step S205 selects the minimum difference value from the difference values corresponding to all the sampling numbers, and determines the sampling number corresponding to the minimum difference value as the target sampling number.
In the embodiment of the invention, the target sampling number of the moving average method is determined by analyzing the historical data of the precise air conditioner in the machine room. Firstly, setting an initial sampling number of a moving average method; then, analyzing the historical data according to the initial sampling number, and calculating the mean value and the standard deviation corresponding to each historical data; then, the differentiation value corresponding to the initial sampling number can be obtained by using the mean value and the standard deviation corresponding to each historical data, namely the differentiation value between the historical data and the mean value corresponding to the historical data under the condition of the initial sampling number; then, continuously adjusting the size of the initial sampling number to obtain a difference value after each adjustment; and finally, selecting the sampling number corresponding to the minimum differentiation value as the target sampling number.
The historical data of the machine room precision air conditioner can be data of the machine room precision air conditioner in a recent period of time. In addition, temperature data of the precise air conditioner in the machine room in a period of time can be analyzed, and the target sampling number corresponding to the temperature is determined, so that if the data to be detected is the temperature to be detected, the upper and lower limit threshold values corresponding to the temperature to be detected are calculated according to the target sampling number corresponding to the temperature, and then the temperature to be detected can be analyzed to judge whether the temperature is the abnormal temperature. Correspondingly, the humidity data of the machine room precision air conditioner in a period of time can be analyzed, the target sampling number corresponding to the humidity is determined, and therefore if the data to be detected is the humidity to be detected, the upper and lower limit threshold values corresponding to the humidity to be detected are calculated according to the target sampling number corresponding to the humidity, the humidity to be detected can be analyzed, and whether the humidity is abnormal or not is judged.
Next, how to determine the target number of samples corresponding to the temperature is explained in detail.
(1) And acquiring the historical temperature of the machine room precision air conditioner, such as the temperature of the machine room precision air conditioner in about 7 days.
The embodiment of the invention can acquire the temperature and the humidity of the precision air conditioner in the machine room at regular time and respectively store the acquired temperature and humidity into the temperature information table and the humidity information table of the precision air conditioner in the machine room. And correspondingly storing the acquisition time corresponding to each temperature and humidity in the temperature information table and the humidity information table. Therefore, the temperature information table stores the orderly-arranged temperatures, and the humidity information table stores the orderly-arranged humidities. In conclusion, the historical temperature of the precision air conditioner in the machine room can be obtained through the temperature information table.
(2) And setting an initial sampling number n corresponding to the temperature. And calculating the mean value corresponding to each historical temperature by combining a moving average method and utilizing the set initial sampling number n.
Specifically, for each historical temperature, sampling data corresponding to the historical temperature, namely (n-1) temperatures before the historical temperature, is obtained. Then, according to the initial sampling number n, the historical temperature and (n-1) temperatures before the historical temperature, calculating the average value corresponding to the historical temperature.
It should be noted that, for the historical temperatures sorted to the top, the number of the temperatures before the historical temperature is not (n-1), and the average value corresponding to the historical temperature cannot be calculated according to the initial sampling number n. Therefore, as an embodiment of the present invention, before obtaining the sample data corresponding to the historical data according to the initial number of samples, the data processing method based on the confidential air conditioner in the machine room may further include: judging whether the difference value between the data quantity before the historical data and the initial sampling quantity is smaller than-1; if so, calculating a mean value corresponding to the historical data according to the data quantity, the data before the historical data and the historical data; if not, acquiring sampling data corresponding to the historical data according to the initial sampling number, and then calculating a mean value corresponding to the historical data. In summary, the average corresponding to the historical temperature can be calculated according to the following formula:
Figure BDA0003000665380000131
in the formula, XiRepresenting the ith historical temperature;
Figure BDA0003000665380000132
and the average value corresponding to the ith historical temperature calculated by using a moving average method is shown, wherein the number of terms of the moving average method is n. Through the formula, the average value corresponding to each historical temperature can be calculated.
(3) And performing differentiation calculation on each historical temperature and the average value corresponding to each historical temperature to obtain a differentiation value corresponding to the initial sampling number n, namely the differentiation value between the historical temperature and the average value corresponding to the historical temperature under the condition of the initial sampling number n. The specific differential value calculation formula is as follows:
Figure BDA0003000665380000133
in the formula, T is the number of days of data corresponding to the acquired historical temperature; m is the number of the precise air conditioners in the machine room corresponding to the acquired historical temperature; i is the acquired historical temperature number corresponding to each air conditioner every day; and E is a differentiation value obtained by calculation according to all historical temperatures and the corresponding average value of the historical temperatures.
(4) After the difference value corresponding to the initial sampling number n is obtained through calculation, the initial sampling number n is continuously adjusted until the adjustment times reach a preset number of times, such as 50 times. After the initial sampling number n is adjusted each time, the difference value corresponding to the sampling number adjusted each time is calculated according to the calculation method of the difference value corresponding to the initial sampling number n described in (1) to (3), so that the difference values corresponding to all the sampling numbers are obtained.
For example, if the initial sampling number n is adjusted to k, for each historical temperature, the sampling data corresponding to the historical temperature, that is, (k-1) temperatures before the historical temperature, is obtained. Then, according to the initial sampling number k, the historical temperature and (k-1) temperatures before the historical temperature, calculating the average value corresponding to the historical temperature. Of course, for the historical temperatures ranked at the top, if the number of the temperatures before the historical temperature is not (k-1), the corresponding average value of the historical temperatures is calculated according to the number of the temperatures before the historical temperatures, the data before the historical temperatures and the historical temperatures.
And after calculating to obtain the differentiation values corresponding to all the sampling numbers, selecting the minimum differentiation value, and determining the sampling number corresponding to the minimum differentiation value as the target sampling number.
The embodiment of the invention can adjust the initial sampling number based on a machine learning algorithm. In the process of adjusting the initial sampling number, a loss function thought of a machine learning algorithm is introduced, and a differentiation value is reduced through continuous learning parameters.
In addition, as an embodiment of the present invention, after calculating the difference value corresponding to the sampling number after each adjustment, it may be further determined whether the calculated difference value is smaller than a preset difference threshold value, if so, the adjustment is ended, and the sampling number corresponding to the calculated difference value is determined as the target sampling number. That is to say, after the initialized sampling number is adjusted each time, the obtained differentiation value is judged, if the differentiation value is smaller than the preset differentiation threshold, the adjustment can be ended, and the sampling number obtained by the adjustment is determined as the target sampling number.
In order to facilitate observation and analysis, after the sampling number corresponding to the minimum differentiation value is determined as the target sampling number, the data processing method based on the machine room confidential air conditioner may further include: determining a target mean value and a target standard deviation corresponding to historical data according to the target sampling number; and calculating an upper threshold and a lower threshold corresponding to the historical data according to the historical data and the target standard deviation corresponding to the historical data and by combining standard deviation factors.
The target mean value is a mean value corresponding to the historical data calculated according to the target sampling number N, and the target standard deviation is a standard deviation corresponding to the historical data calculated according to the target sampling number N. The calculation formula of the mean value has already been described above, and will not be described in detail here. Target standard deviation sigma (N) corresponding to ith historical temperatureiComprises the following steps:
Figure BDA0003000665380000141
after the target mean value and the target standard deviation corresponding to each historical temperature are obtained through calculation, the upper limit threshold and the lower limit threshold corresponding to each historical temperature can be calculated according to a calculation formula of the upper limit threshold and the lower limit threshold and by combining standard deviation factors. The calculation formula of the upper and lower limit thresholds is the same as that of the upper and lower limit thresholds corresponding to the data to be detected, and is not described in detail here.
Further, the data processing method based on the machine room confidential air conditioner may further include: and taking the X axis as the time of the historical data, and taking the Y axis as the target mean value corresponding to the historical data, and the upper limit threshold value and the lower limit threshold value corresponding to the historical data to generate a mean value line, an upper base line and a lower base line corresponding to the historical data so as to be displayed by using a graph.
And distributing the historical data in an XY coordinate system by taking the X axis as the time of the historical data and taking the Y axis as the historical data to obtain a time chart corresponding to the historical data. And distributing the target mean values corresponding to the historical data in an XY coordinate system by taking the X axis as the time of the historical data and the Y axis as the target mean values corresponding to the historical data to obtain a mean value line corresponding to the historical data. And distributing the upper limit threshold corresponding to the historical data in an XY coordinate system by taking the X axis as the time of the historical data and the Y axis as the upper limit threshold corresponding to the historical data to obtain an upper base line corresponding to the historical data. In addition, the lower threshold corresponding to the historical data is distributed in an XY coordinate system by taking the X axis as the time of the historical data and the Y axis as the lower threshold corresponding to the historical data, and the lower base line corresponding to the historical data is obtained. If a certain historical data is out of the range of the upper base line and the lower base line, the historical data is determined to be abnormal data, obviously, a mean line, the upper base line and the lower base line are displayed in an XY coordinate system, and the abnormal data can be found visually.
In addition, the data processing method based on the machine room confidential air conditioner may further include: and generating a mean line, an upper baseline and a lower baseline corresponding to the data to be detected by using the X axis as the time of the data to be detected and the Y axis as the mean value corresponding to the data to be detected and the upper threshold and the lower threshold corresponding to the data to be detected so as to display the mean line, the upper baseline and the lower baseline by using the graph. That is to say, after the historical data and the information related to the historical data can be displayed by using the graph, the data to be detected, the mean value corresponding to the data to be detected, and the upper threshold and the lower threshold corresponding to the data to be detected can be displayed by using the graph, so that a mean value line, an upper baseline and a lower baseline corresponding to the data to be detected can be generated. The mean line, the upper baseline and the lower baseline corresponding to the data can be referred to as a data graph obtained based on a brink analysis algorithm.
In addition, the data processing method based on the confidential air conditioner of the machine room, provided by the embodiment of the invention, can be used for setting the attribute information and the alarm information on the front-end page. Wherein, the attribute information may include: the method comprises the steps of numbering mechanisms of the machine room precise air conditioners, numbering machine rooms of the machine room precise air conditioners, models of the machine room precise air conditioners, numbering equipment in the machine rooms, rated voltage of the air conditioners, rated current of the air conditioners, rated power of the air conditioners, types of the equipment in the machine rooms, sampling number, and starting time and ending time of collection of air conditioner data. The alarm information may include: the mechanism to which the alarm belongs, the name of the alarm, the telephone of the alarm, the department where the alarm is located and the alarm description.
In the embodiment of the invention, the query condition can be input, the time sequence diagram of the data can be queried, and the data diagram can be obtained based on the brink analysis algorithm. The query conditions may include: organization number, raw data query, Boolean algorithm query, data acquisition start time, temperature data acquisition end time, and the like.
For convenience of understanding, the main process of the data processing method based on the machine room confidential air conditioner is described in detail by taking the data to be detected as the temperature to be detected. Fig. 3 is a schematic diagram of the main processes of a data processing method based on a machine room confidential air conditioner according to an embodiment of the present invention. As shown in fig. 3, the main processes of the data processing method based on the machine room confidential air conditioner may include:
step S301, receiving a data processing request, and acquiring the temperature to be detected of the precision air conditioner of the machine room according to the data processing request;
step S302, obtaining N temperatures before the temperature to be detected according to a target sampling number N corresponding to the temperature, wherein N is the number of terms of a moving average method;
step S303, calculating a mean value and a standard deviation corresponding to the temperature to be detected according to the target sampling number N, the temperature to be detected and (N-1) temperatures before the temperature to be detected;
step S304, substituting the standard deviation factor, the mean value and the standard deviation corresponding to the temperature to be detected into an upper threshold value and a lower threshold value calculation formula, and calculating an upper threshold value and a lower threshold value corresponding to the temperature to be detected;
step S305, judging whether the temperature to be detected is not greater than the calculated upper limit threshold and not less than the calculated lower limit threshold, if so, executing step S306, and if not, executing step S307;
step S306, taking the X axis as the time of the temperature to be detected, and taking the Y axis as the mean value corresponding to the temperature to be detected, the upper threshold value and the lower threshold value corresponding to the temperature to be detected so as to generate a mean value line, an upper base line and a lower base line corresponding to the temperature to be detected, and further displaying by using a chart;
and S307, identifying the temperature to be detected as abnormal temperature, inquiring the precise air conditioner of the machine room to which the abnormal temperature belongs, acquiring the contact way of the alarm of the precise air conditioner of the machine room, and sending alarm information.
The target sampling number N is determined according to the above steps S201 to S205, and will not be described in detail here. And if the data to be detected is the humidity to be detected, calculating upper and lower limit thresholds corresponding to the humidity to be detected according to the target sampling number corresponding to the humidity, and further judging whether the humidity to be detected is abnormal humidity.
According to the data processing method based on the machine room confidential air conditioner, the temperature to be detected and the humidity to be detected can be analyzed based on the brink analysis algorithm, the upper and lower limit threshold values corresponding to the temperature to be detected and the humidity to be detected are determined, and then whether the data to be detected is abnormal data can be judged by combining the determined upper and lower limit threshold values, different threshold values can be set for different temperatures and humidities to be detected, the problems that the detection result is inaccurate and the false alarm rate is high due to the fact that a fixed threshold value is set in the prior art are solved, the accuracy of the detection result is improved, the false alarm rate of the machine room confidential air conditioner is reduced, waste of a large amount of manpower is avoided, the calculation speed can be increased and the detection accuracy is further improved due to the adoption of the.
Fig. 4 is a schematic diagram of main modules of a data processing device based on a machine room confidential air conditioner according to an embodiment of the present invention. As shown in fig. 4, the main modules of the data processing apparatus 400 based on the machine room confidential air conditioner include: an acquisition module 401, a determination module 402, an alarm module 403, an algorithm training module 404, and a presentation module 405.
Wherein the obtaining module 401 may be configured to: receiving a data processing request, and acquiring to-be-detected data of the precision air conditioner of the machine room according to the data processing request; the determination module 402 may be configured to: analyzing the data to be detected based on a brink analysis algorithm, and determining upper and lower limit thresholds corresponding to the data to be detected; the alert module 403 may be used to: and if the data to be detected is out of the upper and lower limit threshold range corresponding to the data to be detected, identifying the data to be detected as abnormal data, and alarming the abnormal data. The data to be detected may include: temperature to be detected and humidity to be detected.
As an embodiment of the present invention, the determining module 402 may further be configured to: acquiring sampling data corresponding to the data to be detected according to the target sampling number of the moving average method, wherein the sampling data corresponding to the data to be detected is data before the data to be detected; calculating a mean value and a standard deviation corresponding to the data to be detected according to the target sampling number, the data to be detected and sampling data corresponding to the data to be detected; and substituting the standard deviation factor, the mean value and the standard deviation corresponding to the data to be detected into an upper limit threshold value calculation formula and a lower limit threshold value calculation formula, and calculating the upper limit threshold value and the lower limit threshold value corresponding to the data to be detected.
As an embodiment of the present invention, the algorithm training module 404 may be configured to determine the target number of samples according to the following process: setting an initial sampling number of a moving average method, and acquiring historical data of the precise air conditioner of the machine room; acquiring sampling data corresponding to the historical data according to the initial sampling number, and then calculating an average value corresponding to the historical data according to the initial sampling number, the historical data and the sampling data corresponding to the historical data, wherein the sampling data corresponding to the historical data is data before the historical data; performing differentiation calculation on the historical data and the average value corresponding to the historical data to obtain a differentiation value corresponding to the initial sampling number; adjusting the initial sampling number for preset times according to the differential value corresponding to the initial sampling number, and calculating the differential value corresponding to the sampling number after each adjustment to obtain the differential values corresponding to all the sampling numbers; and selecting the minimum difference value from the difference values corresponding to all the sampling numbers, and determining the sampling number corresponding to the minimum difference value as the target sampling number.
As an embodiment of the invention, algorithm training module 404 may also be configured to: judging whether the calculated differentiation value is smaller than a preset differentiation threshold value or not; if so, finishing the adjustment, and determining the sampling number corresponding to the calculated differentiation value as the target sampling number.
As an embodiment of the invention, algorithm training module 404 may also be configured to: judging whether the difference value between the data quantity before the historical data and the initial sampling quantity is smaller than-1; if so, calculating a mean value corresponding to the historical data according to the data quantity, the data before the historical data and the historical data; if not, acquiring sampling data corresponding to the historical data according to the initial sampling number, and then calculating a mean value corresponding to the historical data.
As an embodiment of the invention, algorithm training module 404 may also be configured to: the initial number of samples is adjusted based on a machine learning algorithm.
As an embodiment of the invention, algorithm training module 404 may also be configured to: determining a target mean value and a target standard deviation corresponding to the historical data according to the target sampling number, wherein the target mean value is a mean value corresponding to the historical data calculated according to the target sampling number, and the target standard deviation is a standard deviation corresponding to the historical data calculated according to the target sampling number; and calculating an upper threshold and a lower threshold corresponding to the historical data according to the historical data and the target standard deviation corresponding to the historical data and by combining standard deviation factors.
As an embodiment of the invention, the display module 405 may be used to: and taking 5 axes as the time of the historical data, and taking the X axis as the target mean value corresponding to the historical data, and the upper limit threshold value and the lower limit threshold value corresponding to the historical data to generate a mean value line, an upper base line and a lower base line corresponding to the historical data so as to display by using a graph.
As an embodiment of the present invention, the alarm module 403 may further be configured to: if the data to be detected is larger than the upper limit threshold value or the data to be detected is smaller than the lower limit threshold value, identifying the data to be detected as abnormal data; and inquiring the machine room precision air conditioner to which the abnormal data belongs, and acquiring the contact way of the alarm person of the machine room precision air conditioner to which the abnormal data belongs so as to send alarm information.
As an embodiment of the invention, display module 405 may also be used to: and taking the 5-axis as the time of the data to be detected, and taking the X-axis as the mean value corresponding to the data to be detected, the upper limit threshold value and the lower limit threshold value corresponding to the data to be detected, and generating a mean value line, an upper base line and a lower base line corresponding to the data to be detected so as to display by using a graph.
According to the data processing device based on the machine room confidential air conditioner, the temperature to be detected and the humidity to be detected can be analyzed based on the brink analysis algorithm, the upper and lower limit threshold values corresponding to the temperature to be detected and the humidity to be detected are determined, and then whether the data to be detected is abnormal data can be judged by combining the determined upper and lower limit threshold values.
Fig. 5 shows an exemplary system architecture 500 to which the data processing method based on the confidential air conditioners of the computer room or the data processing device based on the confidential air conditioners of the computer room according to the embodiment of the present invention may be applied.
As shown in fig. 5, the system architecture 500 may include terminal devices 501, 502, 503, a network 504, and a server 505. The network 504 serves to provide a medium for communication links between the terminal devices 501, 502, 503 and the server 505. Network 504 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 501, 502, 503 to interact with a server 505 over a network 504 to receive or send messages or the like. The terminal devices 501, 502, 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 505 may be a server providing various services, such as a background management server (for example only) providing support in the process of performing data processing based on machine room confidential air conditioners by the user using the terminal devices 501, 502, 503; for another example, the server 505 may perform data processing based on the confidential air conditioners in the computer room according to the embodiment of the present invention.
It should be noted that the data processing method based on the confidential air conditioner in the computer room provided by the embodiment of the present invention is generally executed by the server 505, and accordingly, the data processing device based on the confidential air conditioner in the computer room is generally disposed in the server 505.
It should be understood that the number of terminal devices, networks, and servers in fig. 5 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 6, a block diagram of a computer system 600 suitable for use with a terminal device implementing an embodiment of the invention is shown. The terminal device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program performs the above-described functions defined in the system of the present invention when executed by the Central Processing Unit (CPU) 601.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present invention, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor comprises an acquisition module, a determination module, an alarm module, an algorithm training module and a display module. The names of the modules do not limit the modules themselves under certain conditions, for example, the acquiring module may also be described as a "module that receives a data processing request and acquires data to be detected of the precision air conditioner of the machine room according to the data processing request".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: receiving a data processing request, and acquiring data to be detected of the machine room precision air conditioner according to the data processing request, wherein the data to be detected comprises: measuring the temperature to be detected and the humidity to be detected; analyzing the data to be detected based on a brink analysis algorithm, and determining upper and lower limit thresholds corresponding to the data to be detected; and if the data to be detected is out of the upper and lower limit threshold range corresponding to the data to be detected, identifying the data to be detected as abnormal data, and alarming the abnormal data.
According to the technical scheme of the embodiment of the invention, the temperature to be detected and the humidity to be detected can be analyzed based on the brink analysis algorithm, the upper and lower limit thresholds corresponding to the temperature to be detected and the humidity to be detected are determined, and then the determined upper and lower limit thresholds can be combined to judge whether the data to be detected is abnormal data or not, different thresholds can be set for different humiture to be detected, so that the problems of inaccurate detection result and high false alarm rate caused by setting a fixed threshold in the prior art are solved, the accuracy of the detection result is improved, the false alarm rate of a machine room precision air conditioner is reduced, the waste of a large amount of manpower is avoided, and the brink analysis algorithm can be adopted, the calculation speed can be increased, and the detection precision is further improved.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (17)

1. A data processing method based on a machine room confidential air conditioner is characterized by comprising the following steps:
receiving a data processing request, and acquiring data to be detected of the precision air conditioner of the machine room according to the data processing request, wherein the data to be detected comprises: measuring the temperature to be detected and the humidity to be detected;
analyzing the data to be detected based on a brink analysis algorithm, and determining upper and lower limit thresholds corresponding to the data to be detected;
and if the data to be detected is out of the upper and lower limit threshold range corresponding to the data to be detected, identifying the data to be detected as abnormal data, and alarming the abnormal data.
2. The method according to claim 1, wherein the analyzing the data to be detected based on the brink analysis algorithm to determine upper and lower threshold values corresponding to the data to be detected comprises:
acquiring sampling data corresponding to the data to be detected according to the target sampling number of a moving average method, wherein the sampling data corresponding to the data to be detected is data before the data to be detected;
calculating a mean value and a standard deviation corresponding to the data to be detected according to the target sampling number, the data to be detected and sampling data corresponding to the data to be detected;
and substituting the standard deviation factor, the mean value and the standard deviation corresponding to the data to be detected into an upper limit threshold value calculation formula and a lower limit threshold value calculation formula, and calculating the upper limit threshold value and the lower limit threshold value corresponding to the data to be detected.
3. The method of claim 2, wherein the target number of samples is determined according to the following process:
setting an initial sampling number of a moving average method, and acquiring historical data of the precise air conditioner of the machine room;
calculating a mean value corresponding to the historical data according to the initial sampling number;
performing differentiation calculation on the historical data and the average value corresponding to the historical data to obtain a differentiation value corresponding to the initial sampling number;
and adjusting the initial sampling number for preset times according to the differential value corresponding to the initial sampling number, and determining the target sampling number according to an adjustment result.
4. The method of claim 3, wherein calculating the average corresponding to the historical data according to the initial number of samples comprises:
and acquiring sampling data corresponding to the historical data according to the initial sampling number, and then calculating a mean value corresponding to the historical data according to the initial sampling number, the historical data and the sampling data corresponding to the historical data, wherein the sampling data corresponding to the historical data is data before the historical data.
5. The method according to claim 3, wherein the adjusting the initial number of samples for a preset number of times and determining the target number of samples according to the adjusting result comprises:
adjusting the initial sampling number for preset times, and calculating a differential value corresponding to the sampling number after each adjustment to obtain differential values corresponding to all the sampling numbers;
and selecting the minimum differentiation value from the differentiation values corresponding to all the sampling numbers, and determining the sampling number corresponding to the minimum differentiation value as the target sampling number.
6. The method of claim 5, wherein after calculating the difference value corresponding to each adjusted number of samples, the method further comprises:
judging whether the calculated differentiation value is smaller than a preset differentiation threshold value or not;
if so, finishing the adjustment, and determining the sampling number corresponding to the calculated differentiation value as the target sampling number.
7. The method of claim 4, wherein before obtaining the sample data corresponding to the historical data according to the initial number of samples, the method further comprises:
judging whether the difference value between the data quantity before the historical data and the initial sampling quantity is smaller than-1;
if yes, calculating a mean value corresponding to the historical data according to the data quantity, the previous data of the historical data and the historical data;
if not, acquiring sampling data corresponding to the historical data according to the initial sampling number, and then calculating a mean value corresponding to the historical data.
8. The method of claim 3, further comprising: and adjusting the initial sampling number based on a machine learning algorithm.
9. The method of claim 5, wherein after determining that the number of samples corresponding to the minimum differentiation value is the target number of samples, the method further comprises:
determining a target mean value and a target standard deviation corresponding to the historical data according to the target sampling number;
and calculating an upper threshold and a lower threshold corresponding to the historical data according to the historical data and the target standard deviation corresponding to the historical data and by combining standard deviation factors.
10. The method of claim 9, wherein the target mean is a mean corresponding to the historical data calculated according to the target number of samples, and the target standard deviation is a standard deviation corresponding to the historical data calculated according to the target number of samples.
11. The method of claim 9, further comprising:
and taking an X axis as the time of the historical data, and taking a Y axis as a target mean value corresponding to the historical data, an upper threshold value and a lower threshold value corresponding to the historical data, and generating a mean value line, an upper base line and a lower base line corresponding to the historical data so as to be displayed by using a graph.
12. The method according to claim 2, wherein if the data to be detected is outside the upper and lower threshold ranges corresponding to the data to be detected, identifying the data to be detected as abnormal data, and alarming the abnormal data comprises:
if the data to be detected is larger than the upper threshold value or the data to be detected is smaller than the lower threshold value, identifying the data to be detected as abnormal data;
and inquiring the machine room precision air conditioner to which the abnormal data belongs, and acquiring the contact way of the alarm person of the machine room precision air conditioner to which the abnormal data belongs so as to send alarm information.
13. The method of claim 2, further comprising:
and generating a mean line, an upper base line and a lower base line corresponding to the data to be detected by taking an X axis as the time of the data to be detected and taking a Y axis as a mean value corresponding to the data to be detected and an upper threshold value and a lower threshold value corresponding to the data to be detected so as to display by using a graph.
14. A data processing device based on machine room secret air conditioner is characterized by comprising:
the acquisition module is used for receiving a data processing request and acquiring data to be detected of the precision air conditioner of the machine room according to the data processing request, wherein the data to be detected comprises: measuring the temperature to be detected and the humidity to be detected;
the determining module is used for analyzing the data to be detected based on a brink analysis algorithm and determining upper and lower limit thresholds corresponding to the data to be detected;
and the alarm module is used for identifying the data to be detected as abnormal data and giving an alarm to the abnormal data if the data to be detected is out of the upper and lower limit threshold range corresponding to the data to be detected.
15. The apparatus of claim 14, wherein the determining module is further configured to:
acquiring sampling data corresponding to the data to be detected according to the target sampling number of a moving average method, wherein the sampling data corresponding to the data to be detected is data before the data to be detected;
calculating a mean value and a standard deviation corresponding to the data to be detected according to the target sampling number, the data to be detected and sampling data corresponding to the data to be detected;
and substituting the standard deviation factor, the mean value and the standard deviation corresponding to the data to be detected into an upper limit threshold value calculation formula and a lower limit threshold value calculation formula, and calculating the upper limit threshold value and the lower limit threshold value corresponding to the data to be detected.
16. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-13.
17. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-13.
CN202110345461.2A 2021-03-31 2021-03-31 Data processing method and device based on machine room confidential air conditioner Pending CN112948230A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110345461.2A CN112948230A (en) 2021-03-31 2021-03-31 Data processing method and device based on machine room confidential air conditioner

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110345461.2A CN112948230A (en) 2021-03-31 2021-03-31 Data processing method and device based on machine room confidential air conditioner

Publications (1)

Publication Number Publication Date
CN112948230A true CN112948230A (en) 2021-06-11

Family

ID=76231222

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110345461.2A Pending CN112948230A (en) 2021-03-31 2021-03-31 Data processing method and device based on machine room confidential air conditioner

Country Status (1)

Country Link
CN (1) CN112948230A (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102914328A (en) * 2012-10-23 2013-02-06 深圳市计通智能技术有限公司 Method for automatically regulating alarm thresholds of computer room temperature and humidity monitoring system
CN107086944A (en) * 2017-06-22 2017-08-22 北京奇艺世纪科技有限公司 A kind of method for detecting abnormality and device
CN108921355A (en) * 2018-07-03 2018-11-30 国家计算机网络与信息安全管理中心 A kind of alarm threshold setting method and device based on time series predicting model
US20190370610A1 (en) * 2018-05-29 2019-12-05 Microsoft Technology Licensing, Llc Data anomaly detection
CN111178456A (en) * 2020-01-15 2020-05-19 腾讯科技（深圳）有限公司 Abnormal index detection method and device, computer equipment and storage medium
CN111931860A (en) * 2020-09-01 2020-11-13 腾讯科技（深圳）有限公司 Abnormal data detection method, device, equipment and storage medium
CN112050397A (en) * 2020-08-27 2020-12-08 浙江省邮电工程建设有限公司 Method and system for regulating and controlling temperature of machine room
CN112128950A (en) * 2020-11-24 2020-12-25 北京蒙帕信创科技有限公司 Machine room temperature and humidity prediction method and system based on multiple model comparisons

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102914328A (en) * 2012-10-23 2013-02-06 深圳市计通智能技术有限公司 Method for automatically regulating alarm thresholds of computer room temperature and humidity monitoring system
CN107086944A (en) * 2017-06-22 2017-08-22 北京奇艺世纪科技有限公司 A kind of method for detecting abnormality and device
US20190370610A1 (en) * 2018-05-29 2019-12-05 Microsoft Technology Licensing, Llc Data anomaly detection
CN108921355A (en) * 2018-07-03 2018-11-30 国家计算机网络与信息安全管理中心 A kind of alarm threshold setting method and device based on time series predicting model
CN111178456A (en) * 2020-01-15 2020-05-19 腾讯科技（深圳）有限公司 Abnormal index detection method and device, computer equipment and storage medium
CN112050397A (en) * 2020-08-27 2020-12-08 浙江省邮电工程建设有限公司 Method and system for regulating and controlling temperature of machine room
CN111931860A (en) * 2020-09-01 2020-11-13 腾讯科技（深圳）有限公司 Abnormal data detection method, device, equipment and storage medium
CN112128950A (en) * 2020-11-24 2020-12-25 北京蒙帕信创科技有限公司 Machine room temperature and humidity prediction method and system based on multiple model comparisons

Similar Documents

Publication Publication Date Title
US11169911B2 (en) Method and apparatus for performing a fitting calculation on test data and generating data fluctuation values
CN114396705B (en) Air conditioner fault detection method and device, electronic equipment and medium
CN108228428B (en) Method and apparatus for outputting information
CN111291071B (en) Data processing method and device and electronic equipment
CN110995524B (en) Flow data monitoring method and device, electronic equipment and computer readable medium
CN112446976A (en) Inspection robot, inspection system and inspection method
CN112291370B (en) Method for processing service access relation and related equipment
CN115277261B (en) Abnormal machine intelligent identification method, device and equipment based on industrial control network virus
CN114385869A (en) Method and device for detecting data abnormity, storage medium and computer equipment
CN112182067A (en) Individual height prediction method and device, electronic equipment and storage medium
WO2023134188A1 (en) Index determination method and apparatus, and electronic device and computer-readable medium
CN114780338A (en) Host information processing method and device, electronic equipment and computer readable medium
CN113722369A (en) Method, device, equipment and storage medium for predicting field monitoring data
CN112862222A (en) Air conditioner return air temperature prediction method, abnormality monitoring method and related device
CN111274104B (en) Data processing method, device, electronic equipment and computer readable storage medium
CN112948230A (en) Data processing method and device based on machine room confidential air conditioner
CN114465919B (en) Network service testing method, system, electronic equipment and storage medium
CN114661562A (en) Data warning method, device, equipment and medium
CN111427874B (en) Quality control method and device for medical data production and electronic equipment
CN112132722B (en) Government hot line quantity trend abnormity determining method and device, electronic equipment and medium
CN110633182B (en) System, method and device for monitoring server stability
CN110084298B (en) Method and device for detecting image similarity
CN113129473B (en) Data acquisition method, device and system
CN113986671A (en) Operation and maintenance data anomaly detection method, device, equipment and medium
CN113656391A (en) Data detection method and device, storage medium and electronic equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination