CN111538723A - Monitoring data processing method, device and electronic equipment - Google Patents

Abstract

The application provides a monitoring data processing method, a monitoring data processing device and electronic equipment, wherein the method comprises the following steps: obtaining a variation trend function corresponding to the monitoring data according to the collected monitoring data; extracting data from the variation trend function according to a set time sequence to form an initial data set; and carrying out validity processing on each data point in the initial data set to obtain target monitoring data. By processing the monitoring data, the monitoring data can reflect the state of the object more accurately.

Description

Monitoring data processing method, device and electronic equipment

technical field

The present invention relates to the technical field of data processing, and in particular, to a monitoring data processing method, device and electronic equipment.

Background technique

When it is necessary to perform fault detection or operation and maintenance on the equipment, it is necessary to perform online monitoring of some measurable parameters of the monitored equipment. For example, when the monitored device is a motor, the measurable data generally include temperature, voltage, current, vibration, and the like. Based on these measurable data, time-varying data sequences can be obtained, such as time-varying temperature sequences, voltage rms sequences, current rms sequences, and vibration rms sequences. From these data sequences, the health status and failure trend of the monitored equipment can be further analyzed.

However, during the sampling and recording process, because the monitoring equipment may occasionally be disturbed, the power supply is cut off, or the communication is interrupted, etc., the collected data sequence may lead to misjudgments in the subsequent status evaluation and fault diagnosis of the monitored equipment.

SUMMARY OF THE INVENTION

The purpose of the present invention is to provide a monitoring data processing method, device and electronic equipment, which can enable the monitoring data to more accurately reflect the state of the monitored object.

In a first aspect, an embodiment of the present invention provides a monitoring data processing method, including:

Obtain a change trend function corresponding to the monitoring data according to the collected monitoring data of the monitored equipment;

Extract data from the change trend function according to a set time sequence to form an initial data group;

Validity processing is performed on each data point in the initial data set to obtain target monitoring data.

In an optional implementation manner, performing validity processing on each data point in the initial data set to obtain target monitoring data, including:

Judging whether each data point in the initial data group is an invalid data point according to the preset fluctuation interval and the numerical limit interval;

If there is an invalid data point in the initial data set, the value of the invalid data point is replaced with the value of the specified data point, so as to update the initial data set to obtain target monitoring data.

In the monitoring data processing method provided by the embodiment of the present application, by replacing the invalid points in the initial data group, the probability that the data in the obtained target monitoring data is invalid data points can be greatly reduced, so that the target monitoring data can be greatly reduced. Better representation of the condition of the equipment being monitored.

In an optional implementation manner, performing validity processing on each data point in the initial data set to obtain target monitoring data, including:

Determine initial data points from the initial data set according to a preset numerical limit interval;

According to the preset fluctuation interval, it is judged whether the data points in the initial data group after the initial data point are invalid data points. If the determination value determined by a data point is outside the preset fluctuation range, it indicates that the current data point is an invalid data point. If the current data point in the initial data group is determined by the previous data point of the current data point If the determination value is within the preset fluctuation range, it means that the current data point is a valid data point;

If there is an invalid data point in the initial data set, the value of the invalid data point is replaced with the value of the specified data point, so as to update the initial data set to obtain target monitoring data.

In the monitoring data processing method provided by the embodiment of the present application, the valid initial data points are firstly determined, and after the valid data points are determined, the validity in the subsequent initial data is determined one by one, so that the judgment of the subsequent data points can be made more accurate. Accurate, so that the target monitoring data can better represent the condition of the equipment being monitored.

In an optional implementation manner, the replacing the value of the invalid data point with the value of the specified data point includes:

replacing the value of the invalid data point with the value of a valid data point closest in time to the invalid data point; or,

An objective function is fitted according to the determined valid data points, and the values of the invalid data points are replaced with the values in the objective function.

In the monitoring data processing method provided by the embodiment of the present application, a valid data point with the closest time distance to the invalid data point may be closest to the true value of the invalid data point, so a valid data point with the closest time distance to the invalid data point is used. The value of the data point replaces the value of the invalid data point, so that the data situation at the invalid data point can be better represented, so that the final obtained target monitoring data can be more effective. Alternatively, use data fitting to determine the replacement value of the invalid data point, so that the value of the replaced invalid data point can better represent the condition of the monitored equipment, so that the final target monitoring data can be obtained. More effective.

In an optional implementation manner, the change trend function is a function of time and measurement parameters; and the data is extracted from the change trend function according to a set time sequence to form an initial data group, including:

A plurality of data points with equal time distances are extracted from the change trend function to form an initial data set.

The monitoring data processing method provided by the embodiment of the present application can determine the monitoring data fluctuation range standard by determining the monitoring data of indefinite step length as the monitoring data of equidistant fixed step length. The change of the general monitored equipment quantity has its inherent time constant, and its change within a certain period of time will not exceed a certain value or the change speed will not exceed a certain value. Therefore, equidistant processing also facilitates data transformation such as mean value calculation in different time periods through monitoring data.

In an optional implementation manner, obtaining a change trend function corresponding to the monitoring data according to the collected monitoring data of the monitored device, including:

Data fitting processing is performed on the collected monitoring data to obtain a change trend function corresponding to the monitoring data.

In an optional embodiment, the data fitting process is performed on the collected monitoring data to obtain a change trend function corresponding to the monitoring data, including:

Connecting every two adjacent data points in the collected monitoring data with a straight line to obtain a change trend function including a piecewise linear function; or,

Curve fitting is performed on each data point in the collected monitoring data to obtain a change trend function.

In the monitoring data processing method provided in the embodiment of the present application, the functions corresponding to the monitoring data are determined by fitting in the above-mentioned various ways, so that the subsequent extraction of the initial data group is based on the data of the monitoring data, and will not be separated from the monitoring data, so that it can be The target monitoring data finally determined can better represent the condition of the monitored object.

In an optional embodiment, the monitoring data processing method further includes:

Determine the status score of the monitored equipment according to the target monitoring data;

A target alarm signal is determined based on the state score.

The monitoring data processing method provided by the embodiment of the present application can also use the processed target monitoring data to determine the state of the monitored device, and the processed monitoring data can be used to more accurately monitor the state of the monitored device.

In a second aspect, an embodiment of the present invention provides a monitoring data processing device, including:

an obtaining module for obtaining a change trend function corresponding to the monitoring data according to the collected monitoring data of the monitored equipment;

an extraction module, used for extracting data from the change trend function according to a set time sequence to form an initial data group;

The processing module is configured to perform validity processing on each data point in the initial data set to obtain target monitoring data.

In a third aspect, an embodiment of the present invention provides an electronic device, including: a processor and a memory, where the memory stores machine-readable instructions executable by the processor, and when the electronic device runs, the machine-readable instructions The steps of the method as described in any of the preceding embodiments are performed when executed by the processor.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, the steps of the method described in any of the foregoing embodiments are executed. .

The beneficial effects of the monitoring data processing method, device, electronic device, and computer-readable storage medium provided by the embodiments of the present application include:

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present application more clearly, the following briefly introduces the accompanying drawings that need to be used in the embodiments. It should be understood that the following drawings only show some embodiments of the present application, and therefore do not It should be regarded as a limitation of the scope, and for those of ordinary skill in the art, other related drawings can also be obtained according to these drawings without any creative effort.

FIG. 1 is a schematic block diagram of an electronic device provided by an embodiment of the present application.

FIG. 2 is a flowchart of a monitoring data processing method provided by an embodiment of the present application.

FIG. 3 is a schematic diagram of a data change trend during data processing in the monitoring data processing method provided by the embodiment of the present application.

FIG. 4 is a detailed flowchart of step 203 in the monitoring data processing method provided by the embodiment of the present application.

FIG. 5 is a schematic diagram of another data change trend in the data processing process in the monitoring data processing method provided by the embodiment of the present application.

FIG. 6 is a schematic diagram of a data change trend in still another data processing process in the monitoring data processing method provided by the embodiment of the present application.

FIG. 7 is a schematic diagram of functional modules of a monitoring data processing apparatus provided in an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application.

It should be noted that like numerals and letters refer to like items in the following figures, so once an item is defined in one figure, it does not require further definition and explanation in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

Example 1

In order to facilitate understanding of this embodiment, an electronic device that executes the monitoring data processing method disclosed in the embodiment of this application is first introduced in detail.

As shown in FIG. 1, it is a block diagram of an electronic device. The electronic device 100 may include a memory 111 , a memory controller 112 , a processor 113 , a peripheral interface 114 , an input and output unit 115 , and a display unit 116 . Those of ordinary skill in the art can understand that the structure shown in FIG. 1 is only for illustration, and does not limit the structure of the electronic device 100 . For example, the electronic device 100 may also include more or fewer components than shown in FIG. 1 , or have a different configuration than that shown in FIG. 1 .

The above-mentioned elements of the memory 111 , the storage controller 112 , the processor 113 , the peripheral interface 114 , the input/output unit 115 and the display unit 116 are directly or indirectly electrically connected to each other to realize data transmission or interaction. For example, these elements may be electrically connected to each other through one or more communication buses or signal lines. The above-mentioned processor 113 is used to execute executable modules stored in the memory.

Wherein, the memory 111 may be, but not limited to, a random access memory (Random Access Memory, referred to as RAM), a read only memory (Read Only Memory, referred to as ROM), a programmable read only memory (Programmable Read-Only Memory, referred to as PROM) , Erasable Programmable Read-Only Memory (Erasable Programmable Read-Only Memory, referred to as EPROM), Electrically Erasable Read-Only Memory (Electric Erasable Programmable Read-Only Memory, referred to as EEPROM) and so on. The memory 111 is used to store a program, and the processor 113 executes the program after receiving the execution instruction, and the method executed by the electronic device 100 defined by the process disclosed in any of the embodiments of this application can be applied to processing in the processor 113 , or implemented by the processor 113 .

The above-mentioned processor 113 may be an integrated circuit chip with signal processing capability. The above-mentioned processor 113 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; it may also be a digital signal processor (Digital signal processor, DSP for short) , Application Specific Integrated Circuit (ASIC), Field Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components. The methods, steps, and logic block diagrams disclosed in the embodiments of this application can be implemented or executed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The aforementioned peripheral interface 114 couples various input/output devices to the processor 113 and the memory 111 . In some embodiments, peripheral interface 114, processor 113, and memory controller 112 may be implemented in a single chip. In other instances, they may be implemented by separate chips.

The above-mentioned input and output unit 115 is used for inputting data from sensing devices such as sensors, and outputting processed result data to a computer, a server, or the like. The input and output unit 115 may be, but not limited to, a communication port or the like.

The above-mentioned display unit 116 provides an interactive interface (eg, a user operation interface) between the electronic device 100 and the user or is used to display image data for the user's reference. In this embodiment, the display unit may be a liquid crystal display or a touch display. In the case of a touch display, it can be a capacitive touch screen or a resistive touch screen that supports single-point and multi-touch operations. Supporting single-point and multi-touch operation means that the touch display can sense the touch operation from one or more positions on the touch display at the same time, and hand over the sensed touch operation to the processor. calculation and processing.

The electronic device 100 in this embodiment may be used to execute each step in each method provided in this embodiment of the present application. The implementation process of the monitoring data processing method will be described in detail below through several embodiments.

Embodiment 2

Please refer to FIG. 2 , which is a flowchart of a monitoring data processing method provided by an embodiment of the present application. The specific flow shown in FIG. 2 will be described in detail below.

Step 201: Obtain a change trend function corresponding to the monitoring data according to the collected monitoring data of the monitored device.

In one embodiment, when the monitored device is a motor, the above-mentioned monitoring data may include temperature, current amplitude or effective value, voltage amplitude or effective value, vibration displacement amplitude or effective value, vibration velocity amplitude or One or more of data such as effective value, vibration acceleration amplitude or effective value.

Taking the monitoring data as one kind of data as an example, the data sequences corresponding to the monitoring data obtained by sampling may be t0[k0] and x0[k0]. Wherein, k0=1～m, wherein m is a positive integer greater than one. Among them, t0[k0] represents any point in time, and x0[k0] represents the monitoring data value sampled by t0[k0].

In one example, data sequences t0[k0] and x0[k0] of monitoring data are obtained by sampling, and k0=1˜m. If the currently sampled monitoring data is the vibration velocity amplitude. where m=8. The data sequence of the monitoring data is shown in Table 1 below.

Table 1

k0 t0[k] x0[k] 1 0 1.523 2 twenty four 0.2614 3 51 0.7087 4 73 0.6943 5 102 1.000 6 128 0.6752 7 148 0.679 8 175 0.6801

Wherein, the unit of t0 is second (s), and the unit of x0 is millimeter/second (mm/s).

Optionally, data fitting processing is performed on the collected monitoring data to obtain a change trend function corresponding to the monitoring data.

In an embodiment, every two adjacent data points in the collected monitoring data are connected by a straight line, so as to obtain a change trend function including a piecewise linear function.

Taking the above example as an example, as shown in Figure 3, each data point of the monitoring data is represented by "○". Every two adjacent data points are connected by a straight line to form a one-dimensional linear function. Among them, the independent variable of each one-dimensional linear function is the time variable, and the dependent variable of the function is the vibration velocity amplitude variable.

In another embodiment, curve fitting is performed on each data point in the collected monitoring data to obtain a change trend function.

Alternatively, a polynomial curve can be used to achieve a curve fit to the monitoring data.

Step 202: Extract data from the change trend function according to a set time sequence to form an initial data group.

Optionally, a plurality of data points with equal time distances are extracted from the change trend function to form an initial data set.

Exemplarily, an equidistant time series t[k] may be given, where t=1∼n, where n is a positive integer greater than one. In this embodiment, the value of n may be greater than the value of m.

In one example, t[1]=t0[1], t[n]=t0[m], and the interval of the t[k] time series is dt=(t[n]-t[1])/( n-1), n≥2. Taking t[k] as the independent variable, and using the change trend function formed by the data series t0[k0] and x[k0], the dependent variable x[k] is obtained, so as to obtain the data series t[k] and x[ of the initial data set k].

In an example, the value of n may be 11, t[1]=t0[1]=0, t[11]=t0[8]=175, and the interval of the time series is dt=175/10=17.5. Using the change trend function formed by connecting the data series t0[k0] and x0[k0], the dependent variable x[k] is obtained, thereby obtaining the interpolated series t[k] and x[k].

As shown in FIG. 3, each data point in the extracted initial data set is represented by "△". The value of the monitoring data corresponding to t[k] can be extracted from the change trend function, and an initial data group can be formed.

The data sequence x[k] of the initial data set can be, as shown in Table 2 below.

Table 2

k t[k] x[k] 1 0 1.523 2 17.5 0.603 3 35 0.444 4 52.5 0.708 5 70 0.696 6 87.5 0.847 7 105 0.963 8 122.5 0.744 9 140 0.677 10 157.5 0.679 11 175 0.680

where t is in seconds (s) and x is in millimeters per second (mm/s).

In this embodiment, by extracting the initial data group from the above-mentioned change trend function, the monitoring data of indeterminate step size can be changed into the initial data group of equidistant and fixed step size, which is convenient to do different time periods through the extracted data. Data transformations such as mean calculation.

As far as the monitored device is a motor, the change due to the damage to the motor's health can be considered as a gradual data change, and the range and rate of change are within a certain range. The change of various data of the motor has its inherent time constant, and its change within a certain period of time will not exceed a certain value or the change speed will not exceed a certain value. The jump data generated by the sudden and severe fault of the motor is not suitable for the data of fault diagnosis and predictive maintenance of the motor. Therefore, validity processing can be performed on each data point in the initial data set, and invalid data points in it can be eliminated or replaced.

Step 203: Perform validity processing on each data point in the initial data set to obtain target monitoring data.

In one embodiment, as shown in FIG. 4 , step 203 may include the following steps.

Step 2031: Determine an initial data point from the initial data set according to a preset numerical limit interval.

Optionally, the above-mentioned numerical limit interval can be set to different values according to different monitored devices. For example, when the monitored device is a motor and the monitored data is the vibration velocity amplitude of the motor, the numerical limit interval may include an upper limit and a lower limit respectively. For example, the upper limit x_max may be a value such as 1.0, 1.1, 1.2, and the lower limit x_min may be a value such as 0.3, 0.25, 0.28, 0.32, and the like.

In this embodiment, the above-mentioned initial data point may be the first valid data point in the initial data group.

In this embodiment, the data points before the initial data points in the initial data group are determined to be invalid data points.

Step 2032, according to a preset fluctuation interval, determine whether the data points in the initial data group after the initial data point are invalid data points.

Wherein, if the difference between the current data point in the initial data set and the previous data point is outside the preset fluctuation range, it indicates that the current data point is an invalid data point.

Wherein, if the determination value determined by the current data point in the initial data group and the previous data point of the current data point is outside the preset fluctuation range, it indicates that the current data point is an invalid data point, if the If the determination value determined between the current data point in the initial data set and the previous data point of the current data point is within the preset fluctuation interval, it indicates that the current data point is a valid data point.

Optionally, the above-mentioned fluctuation interval may include a numerical fluctuation interval, a slope fluctuation interval, and a power function ratio fluctuation interval.

The power function ratio can be expressed as: km=(x2-x1)^n/(t2-t1). The previous data point is represented as (t1, x1), the current data point is represented as (t2, x2), and n is a real number greater than 0.

In this embodiment, the determination value determined between the current data point and the previous data point may be the difference between the value of the current data point and the value of the previous valid data point; the current data point in the initial data group and the previous data point are determined The determination value of can also be the slope of the line segment formed by the current data point and the previous valid data point.

Optionally, determine whether the difference between the value of the current data point and the value of the previous valid data point is within the numerical fluctuation range, if the difference between the value of the current data point and the value of the previous valid data point is within the numerical fluctuation range, then Indicates that the current data point is a valid data point.

Optionally, determine whether the slope of the line segment formed by the current data point and the previous valid data point is within the slope fluctuation range, and if the slope of the line segment formed by the current data point and the previous valid data point is within the slope fluctuation range, it means that the current Data points are valid data points.

Optionally, determine whether the power function ratio formed by the current data point and the previous valid data point is within the power function ratio fluctuation range, if the power function ratio formed by the current data point and the previous valid data point is within the power function ratio fluctuation range. , it means that the current data point is a valid data point.

Optionally, determine whether the difference between the value of the current data point and the value of the previous valid data point is within the numerical fluctuation range, and whether the slope of the line segment formed by the current data point and the previous valid data point is within the slope fluctuation range; if The difference between the value of the current data point and the value of the previous valid data point is within the numerical fluctuation range, and the slope of the line segment formed by the current data point and the previous valid data point is within the slope fluctuation range, indicating that the current data point is valid data point.

Optionally, determine whether the difference between the value of the current data point and the value of the previous valid data point is within the numerical fluctuation range, and whether the power function ratio formed by the current data point and the previous valid data point is within the power function ratio fluctuation range. ;If the difference between the value of the current data point and the value of the previous valid data point is within the numerical fluctuation range, and the power function ratio formed by the current data point and the previous valid data point is within the power function ratio fluctuation range, it means that the current data Points are valid data points.

Exemplarily, the numerical fluctuation interval may include an upper numerical limit and a numerical lower limit. In one example, the upper numerical limit is expressed as xw_max=a, and the lower numerical limit is xw_min=b. Among them, the values of a and b may be different according to the collected monitoring data. For example, when the collected monitoring data is the vibration speed amplitude of the motor, the value of the above a can be 0.3, 0.35, 0.4 and the like, and the value of b can be -0.3, -0.35, -0.4 and the like.

Exemplarily, the slope fluctuation interval may include an upper slope limit and a lower slope limit. In one example, the upper slope limit is expressed as kxw_max=c, and the lower slope limit is kxw_min=d. Among them, the values of c and d may be different according to the collected monitoring data. For example, when the collected monitoring data is the vibration velocity amplitude of the motor, the value of c above can be 0.01, 0.013, 0.018, 0.015, etc., and the value of d can be -0.01, -0.013, -0.018, -0.015, etc. value.

Optionally, whether each data point in the initial data group is a valid data point may be separately recorded through a record array. Exemplarily, if one of the values in the record array is assigned as the first value, it indicates that the data point corresponding to the value is a valid data point; if one of the values in the record array is assigned as the second value, it indicates that the value corresponds to is an invalid data point. In one example, the first value is a non-zero value; the second value is zero.

In one example, the record array may be flag[k], k=1˜n, and flag[k] indicates the validity of the kth data. When flag[k1]=1, the k1th data points t[k1] and x[k1] in the corresponding initial data group are valid data points. When flag[k2]=0, the k2th data points t[k2] and x[k2] in the corresponding initial data group are invalid data points.

Step 2033, if there is an invalid data point in the initial data set, replace the value of the invalid data point with the value of the specified data point, so as to update the initial data set to obtain target monitoring data.

In one embodiment, step 2033 may be implemented as: replacing the value of the invalid data point with the value of a valid data point whose time distance is closest to the invalid data point.

Optionally, a new array can be used to store target monitoring data. For example, target monitoring data can be recorded using t[k] and y[k].

Exemplarily, when flag[i]=1, then y[i]=x[i], where i is a positive integer. Exemplarily, when flag[j]=0, then y[j]=y[j-1], where j is a positive integer greater than two.

Exemplarily, when flag[1]=0, and flag[c]=1; then y[1]=x[c]. Among them, c is a positive integer greater than one, and flag[r] is zero, and r ranges from 1 to c-1.

The processing flow of the above steps 2031-2033 is described below through a specific logic:

p from 1 to n: if x_min≤x[p]≤x_max, then x_z=x[p], t_z=t[p], and jump out of the loop; otherwise, p=p+1 to continue the loop. In this way, the first valid data point is determined and recorded as t_z and x_z, and t[p] and x[p] are marked as valid points, that is, flag[p]=1.

The preprocessed data value is y[k], 1～n, and the initial value is assigned 0.

k from 1 to p: y[k]=x_z. Determine the first P values in the target monitoring data.

Among them, the data points t_z and x_z are temporary variables used in the judgment process, and are used to store the current valid data points in the judgment process.

According to the above processing flow, based on the data in Table 2 above, the upper limit and lower limit of the numerical limit interval are respectively x_max=1.0 and x_min=0.3; the upper limit and lower limit of the numerical value fluctuation interval are respectively xw_max=0.3, xw_min= -0.3; and the upper and lower slope limits of the slope fluctuation range are respectively kxw_max=0.01, kxw_min=-0.01 as an example to describe:

When p=1, x[1]=1.523, 1.523>1.0, continue the cycle; when p=2, x[2]=0.603, 0.3≤0.603≤1.0, then x_z=0.603, t_z=17.5, flag[2 ]=1, y[1]=x_z=0.603, y[2]=x_z=0.603. Therefore, the second data point can be determined to be the initial data point.

After the initial data points are determined, it can be determined whether the data points in the initial data group after the initial data points are invalid data points according to the preset fluctuation interval. Illustratively,

Then, let p=p+1, t_n=t[p], x_n=x[p]; calculate the slope: kxw=(x_n-x_z)/(t_n-t_z); calculate the deviation: xw=x_n-x_z; when When kxw_min≤kxw≤kxw_max and w_min≤xw≤xw_max, then t_z=t[p], x_z=x[p], flag[p]=1; otherwise, flag[p]=0, y[p]=x_z.

According to the above processing flow, based on the data in Table 2 above, the upper limit and lower limit of the numerical limit interval are respectively x_max=1.0 and x_min=0.3; the upper limit and lower limit of the numerical value fluctuation interval are respectively xw_max=0.3, xw_min= -0.3; and the upper and lower slope limits of the slope fluctuation interval are respectively kxw_max=0.01, kxw_min=-0.01 as an example to describe, the judgment processing flow for the data points after the second data point in the initial data set can be expressed as :

Let p=3, t_n=t[3]=35, x_n=x[3]=0.444;

Calculate the slope: kxw=(x_n-x_z)/(t_n-t_z)=(0.444-0.603)/(35-17.5)=-0.009086;

Calculated deviation: xw=-0.159;

Because -0.01≤-0.009086≤0.01 and -0.3≤-0.159≤0.3 hold, so t_z=t[p]=t[3]-35; x_z=x[p]=x[3]=0.444; flag[p ]=flag[3]=1; y[p]=y[3]=x_z=0.444.

Then, execute the next cycle: let p=p+1=4, t_n=t[4]=52.5, x_n=x[4]=0.708;

Calculate the slope: kxw=(x_n-x_z)/(t_n-t_z)=(0.708-0.444)/(52.5-35)=0.0151;

Calculated deviation; xw = 0.264;

Because 0.0151≥0.01 does not hold, so flag[p]=flag[4]=0; y[p]=y[4]=x_z=0.444;

And so on until p>n.

Taking the above example as an example, the determined flag[k] array may be as shown in Table 3 below.

table 3

As shown in FIG. 5 , the target monitoring data obtained by processing the initial data set shown in Table 2 through the above steps. Among them, the "○" shown in Fig. 5 represents the data point in the initial data set, and the "△" shown in Fig. 5 represents the data point in the target monitoring data.

In another embodiment, step 2033 may be implemented as: fitting an objective function according to the determined valid data points; and replacing the values in the objective function with the values of the invalid data points.

In this embodiment, the above-mentioned objective function may be a linear function or a curved function.

The following description takes the initial data set as the data in Table 2 as an example:

Optionally, if there are eight valid data points in the initial data set under this example, the second data point and the third data point can be fitted into a first straight line function; then according to the first straight line The function determines the replacement value corresponding to the first data point;

The fifth data point, the sixth data point and the seventh data point are fitted to the second straight line function, or the fifth data point and the sixth data point are fitted to the second straight line function; The two-line function determines the replacement value corresponding to the fourth data point;

The ninth data point, the tenth data point and the eleventh data point are fitted to a third straight line function, or the ninth data point and the tenth data point are fitted to a third straight line function; then according to The third line function determines the replacement value corresponding to the eighth data point.

Optionally, with the second data point, the third data point, the fifth data point, the sixth data point, the seventh data point, the ninth data point, the tenth data point and the eleventh data point Curve fitting is performed on the data points to obtain a curve function. Then, the value corresponding to the first data point, the value corresponding to the fourth data point, and the replacement value corresponding to the eighth data point can be determined according to the curve function.

As shown in FIG. 6 , the target monitoring data obtained by processing the initial data set shown in Table 2 through the above steps. Among them, "○" shown in Fig. 6 represents the valid data points in the initial data set, and "△" shown in Fig. 6 represents the data points in the target monitoring data.

In another embodiment, step 203 may also include the following steps.

Step 2034: Determine whether each data point in the initial data set is an invalid data point according to a preset fluctuation interval and a numerical limit interval.

Exemplarily, the numerical limit interval may represent a limit on the value of each data point in the initial data set. If the value of each data point in the initial data set is within the numerical limit, it means that the data point may be a valid data point. If the value of each data point in the initial data set is within the numerical limit range, it means that the data point is an invalid data point.

Optionally, the above-mentioned fluctuation interval may include a numerical fluctuation interval and a slope fluctuation interval.

Optionally, determine whether the difference between the value of the current data point and the value of the previous valid data point is within the numerical fluctuation range, if the difference between the value of the current data point and the value of the previous valid data point is within the numerical fluctuation range, then Indicates that the current data point is a valid data point.

Optionally, determine whether the slope of the line segment formed by the current data point and the previous valid data point is within the slope fluctuation range, and if the slope of the line segment formed by the current data point and the previous valid data point is within the slope fluctuation range, it means that the current Data points are valid data points.

Optionally, it is judged whether the value of the current data point is within the numerical limit range; if the value of each data point in the initial data group is within the numerical limit range, it means that the data point is a valid data point. If the value of each data point in the initial data set is within the numerical limit, it means that the data point is invalid.

Optionally, determine whether the difference between the value of the current data point and the value of the previous valid data point is within the numerical fluctuation range, and whether the slope of the line segment formed by the current data point and the previous valid data point is within the slope fluctuation range; if The difference between the value of the current data point and the value of the previous valid data point is within the numerical fluctuation range, and the slope of the line segment formed by the current data point and the previous valid data point is within the slope fluctuation range, indicating that the current data point is valid data point.

Optionally, determine whether the difference between the value of the current data point and the value of the previous valid data point is within the numerical fluctuation range, whether the slope of the line segment formed by the current data point and the previous valid data point is within the slope fluctuation range, and the current Whether the value of the data point is within the numerical limit range; if the value of each data point in the initial data set is within the numerical limit range, and the difference between the value of the current data point and the value of the previous valid data point is within the numerical fluctuation range, And if the slope of the line segment formed by the current data point and the previous valid data point is within the slope fluctuation range, it means that the current data point is a valid data point.

Exemplarily, the numerical fluctuation interval may include an upper numerical limit and a numerical lower limit. In one example, the upper numerical limit is expressed as xw_max=a, and the lower numerical limit is xw_min=b. Among them, the values of a and b may be different according to the collected monitoring data. For example, when the collected monitoring data is the vibration speed amplitude of the motor, the value of the above a can be 0.3, 0.35, 0.4 and the like, and the value of b can be -0.3, -0.35, -0.4 and the like.

Exemplarily, the slope fluctuation interval may include an upper slope limit and a lower slope limit. In one example, the upper slope limit is expressed as kxw_max=c, and the lower slope limit is kxw_min=d. The values of c and d may be different according to the collected monitoring data. For example, when the collected monitoring data is the vibration velocity amplitude of the motor, the value of c above can be 0.01, 0.013, 0.018, 0.015, etc., and the value of d can be -0.01, -0.013, -0.018, -0.015, etc. value.

Optionally, whether each data point in the initial data group is a valid data point may be separately recorded through a record array. Exemplarily, if one of the values in the record array is assigned as the first value, it indicates that the data point corresponding to the value is a valid data point; if one of the values in the record array is assigned as the second value, it indicates that the value corresponds to is an invalid data point. In one example, the first value is a non-zero value; the second value is zero.

In one example, the record array may be flag[k], k=1˜n, and flag[k] indicates the validity of the kth data. When flag[k1]=1, the k1th data points t[k1] and x[k1] in the corresponding initial data group are valid data points. When flag[k2]=0, the k2th data points t[k2] and x[k2] in the corresponding initial data group are invalid data points.

Step 2035, if there is an invalid data point in the initial data set, replace the value of the invalid data point with the value of the specified data point to update the initial data set to obtain target monitoring data.

Optionally, a new array can be used to store target monitoring data. For example, target monitoring data can be recorded using t[k] and y[k].

Exemplarily, when flag[i]=1, then y[i]=x[i], where i is a positive integer. Exemplarily, when flag[j]=0, then y[j]=y[j-1], where j is a positive integer greater than two.

Exemplarily, when flag[1]=0, and flag[c]=1; then y[1]=x[c]. Among them, c is a positive integer greater than one, and flag[r] is zero, and r is a positive integer ranging from 1 to c-1. Further, if c is greater than two, let y[s]=x[c], where s is a positive integer ranging from 1 to c-1.

Through the above steps, the monitoring data of the monitored equipment can be preprocessed, so that the processed target monitoring data can better represent the condition of the monitored equipment.

In this embodiment, the status of the monitored device can also be identified according to the above-mentioned target monitoring data.

After step 203, the method may further include: determining a state score of the monitored device according to the target monitoring data; and determining a target alarm signal according to the state score.

Exemplarily, the above-mentioned target alarm signal may be no alarm signal; or may be alarm signals of different levels.

Taking the monitored equipment as the motor and the monitoring data as the temperature rise data T of the motor as an example, the evaluation score is obtained by the following piecewise linear evaluation function.

In an example, the correspondence between the respective threshold parameters T ₁ , T ₂ , T ₃ , T ₄ , T ₅ values and evaluation scores in the above formula is shown in Table 4 below.

Table 4

Threshold parameter value T₁ T₂ T₃ T₄ T₅ assessment score 100 75 50 25 0

In one instance, for one motor, the threshold parameters can be given as shown in Table 5 below.

table 5

Threshold parameter T₁ T₂ T₃ T₄ T₅ value 60 65 70 75 80

In this embodiment, the number of the above threshold parameters and the values of the threshold parameters are not limited to the above examples. Specifically, the threshold parameters can be determined according to the monitored device and monitoring data.

Optionally, the working state of the motor can be divided into: normal state, suspicious state, bad state and dangerous state. Depending on the state, different alarms can be output.

Exemplarily, the states of different motors may correspond to different standards. Examples are as follows:

1) The normal state refers to the state where the evaluation score is between 75 and 100, and there is no alarm;

2) Suspicious status refers to the status of the evaluation score between 50 and 75 (excluding 75), which triggers an intelligent early warning signal;

3) Bad state refers to the state where the evaluation score is between 25 and 50 (excluding 50), which triggers an ordinary early warning signal;

4) Dangerous state refers to the state where the evaluation score is between 0 and 25 (excluding 25), and an emergency alarm signal is triggered.

Optionally, when the target alarm signal is an alarm signal of different levels, the target alarm signal may be sent to the server, or to a designated communication account.

The alarm signal should be uploaded to the cloud platform immediately, and the operation and maintenance personnel should be notified through the cloud platform.

From the above examples, we can know that:

If the corresponding temperature rise is 65K and below, an evaluation score of no less than 75 points will be obtained, and there will be no alarm;

If the corresponding temperature rise is 70K and below, and above 65K (65K may be excluded), an evaluation score of 50 to 75 points (75 may be excluded) will be obtained, triggering an intelligent early warning signal;

If the corresponding temperature rise is 75K and below, and above 70K (excluding 70K), an evaluation score of 25 to 50 points (excluding 50 points) will be obtained, triggering an ordinary early warning signal;

If the corresponding temperature rise is 80K and below, and above 75K (excluding 75K), an evaluation score of 0 to 25 points (excluding 25 points) will be obtained, and an emergency alarm signal will be triggered.

where K stands for Kelvin, the unit of temperature in the International System of Units.

It can be known that if the temperature rise monitoring data has not been preprocessed in the above steps 201-203, if there is an interference signal with a temperature rise greater than 75K, it will cause false alarms such as emergency alarms and affect the operation of the equipment.

Further, the motor operation and maintenance service system can also predict the specific time when the motor should be maintained according to the trend of the evaluation parameter scores related to the motor loss characteristics.

Exemplarily, the evaluation parameter evaluation score related to the loss characteristic may include a current evaluation score, a voltage evaluation score, a vibration evaluation score, a temperature evaluation score, and the like. According to the preset evaluation score maintenance threshold parameter of the operation and maintenance service system, the specific content and time of the next maintenance are given. The evaluation score maintenance threshold can be a value between the smart alert threshold and the normal alert threshold.

The trend of the evaluation score refers to the rate of change of the evaluation score in a certain period, which is the slope of the linear regression of the previous operating cycle. The operating cycle refers to the main cycle of the motor work, which can be days, weeks, months, quarters, years and other cycles.

For example, in the on-line monitoring of motor temperature rise, the motor temperature rise has a sudden high value due to interference, which will cause the rate of change of the evaluation score in a certain period to be too large, so the system will calculate that the system will be in a very short time. Reaching a lower score within the period would falsely trigger an alarm for maintenance.

In addition, the occurrence of interference signals that suddenly increase or decrease in monitoring data will also affect fault diagnosis. The fault diagnosis of the motor will mainly be based on the comparison result between the monitoring data of the motor and the predetermined threshold parameters. Once an abnormally large or too small signal appears, it will make the fault diagnosis of the motor misjudged. For example, excessive temperature rise caused by interference will be judged as failure of the motor such as phase loss, overload, air blockage, fan damage or inter-turn short circuit.

Through the monitoring data processing method in the embodiment of the present application, abnormalities not caused by motor faults can be eliminated, for example, invalid data caused by interference, power failure or communication interruption of the acquisition and transmission equipment, thereby improving target monitoring. data validity.

Embodiment 3

Based on the same application concept, the embodiment of the present application also provides a monitoring data processing device corresponding to the monitoring data processing method. For the implementation of the apparatus in the embodiment, reference may be made to the description in the embodiment of the foregoing method, and repeated descriptions will not be repeated.

Please refer to FIG. 7 , which is a schematic diagram of functional modules of a monitoring data processing apparatus provided by an embodiment of the present application. Each module in the monitoring data processing apparatus in this embodiment is used to execute each step in the foregoing method embodiment. The monitoring data processing device includes a obtaining module 301, an extraction module 302, and a processing module 303; wherein,

Obtaining module 301 is used to obtain a change trend function corresponding to the monitoring data according to the collected monitoring data of the monitored equipment;

Extraction module 302, for extracting data according to the set time sequence from the change trend function to form an initial data group;

The processing module 303 is configured to perform validity processing on each data point in the initial data set to obtain target monitoring data.

In a possible implementation, the processing module 303 includes: a first judgment unit and a first replacement unit;

The first judgment unit is used for judging whether each data point in the initial data group is an invalid data point according to a preset fluctuation interval and a numerical limit interval, wherein, if the current data point in the initial data group and the If the determination value determined by the previous data point of the current data point is outside the preset fluctuation range, it indicates that the current data point is an invalid data point. A determination value determined by a data point is within the preset fluctuation range, indicating that the current data point is a valid data point;

The first replacement unit is used to replace the value of the invalid data point with the value of the specified data point if there is an invalid data point in the initial data set, so as to update the initial data set to obtain the target monitoring data.

In a possible implementation, the first replacement unit is used for:

The value of the invalid data point is replaced with the value of a valid data point whose time distance is closest to the invalid data point.

In a possible implementation, the first replacement unit is used for:

Fit the objective function according to the determined valid data points;

Replace the value of the invalid data point with the value in the objective function.

In a possible implementation, the processing module 303 includes: a determination unit, a second judgment unit and a second replacement unit:

a determining unit, configured to determine an initial data point from the initial data group according to a preset numerical limit interval;

A second judging unit, configured to judge, according to a preset fluctuation interval, whether a data point in the initial data group after the initial data point is an invalid data point, wherein, if the current data point in the initial data group is the same as the The determination value determined by the previous data point of the current data point is outside the preset fluctuation range, indicating that the current data point is an invalid data point. If the current data point in the initial data group is the same as the current data point If the determination value determined by the previous data point of , is within the preset fluctuation interval, it means that the current data point is a valid data point;

The second replacement unit is configured to replace the value of the invalid data point with the value of the specified data point if there is an invalid data point in the initial data set, so as to update the initial data set to obtain the target monitoring data.

In a possible implementation, the second replacement unit is used for:

The value of the invalid data point is replaced with the value of a valid data point whose time distance is closest to the invalid data point.

In a possible implementation, the second replacement unit is used for:

Fit the objective function according to the determined valid data points;

Replace the value of the invalid data point with the value in the objective function.

In a possible implementation, the extraction module 302 is configured to extract a plurality of data points with equal time distances from the change trend function to form an initial data set.

In a possible implementation manner, the obtaining module 301 is configured to perform data fitting processing on the collected monitoring data to obtain a change trend function corresponding to the monitoring data.

In a possible implementation, the module 301 is obtained for:

Connecting every two adjacent data points in the collected monitoring data with a straight line to obtain a change trend function including a piecewise linear function; or,

Curve fitting is performed on each data point in the collected monitoring data to obtain a change trend function.

In a possible implementation, the monitoring data processing device may further include:

a first determining module, configured to determine the state score of the monitored device according to the target monitoring data;

The second determination module is configured to determine the target alarm signal according to the state score.

In addition, an embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is run by a processor, the monitoring data processing method described in the above method embodiment is executed. step.

The computer program product of the monitoring data processing method provided by the embodiments of the present application includes a computer-readable storage medium storing program codes, and the instructions included in the program codes can be used to execute the monitoring data processing methods described in the above method embodiments. For details, refer to the above method embodiments, which will not be repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may also be implemented in other manners. The apparatus embodiments described above are merely illustrative, for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architectures, functions and possible implementations of apparatuses, methods and computer program products according to various embodiments of the present application. operate. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more functions for implementing the specified logical function(s) executable instructions. 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 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 is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented in dedicated hardware-based systems that perform the specified functions or actions , or can be implemented in a combination of dedicated hardware and computer instructions.

In addition, each functional module in each embodiment of the present application may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes . It should be noted that, in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any relationship between these entities or operations. any such actual relationship or sequence exists. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device that includes a list of elements includes not only those elements, but also includes not explicitly listed or other elements inherent to such a process, method, article or apparatus. Without further limitation, an element defined by the phrase "comprises" does not preclude the presence of additional identical elements in a process, method, article, or device that includes the element.

The above descriptions are only preferred embodiments of the present application, and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included within the protection scope of this application. It should be noted that like numerals and letters refer to like items in the following figures, so once an item is defined in one figure, it does not require further definition and explanation in subsequent figures.

The above are only specific embodiments of the present application, but the protection scope of the present application is not limited to this. should be covered within the scope of protection of this application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (10)

1. A method for processing monitoring data, comprising:

obtaining a variation trend function corresponding to the monitoring data according to the collected monitoring data of the monitored equipment;

extracting data from the change trend function according to a set time sequence to form an initial data set;

and carrying out effectiveness processing on each data point in the initial data set to obtain target monitoring data.

2. The method of claim 1, wherein the validation processing of each data point in the initial data set to obtain target monitoring data comprises:

judging whether each data point in the initial data set is an invalid data point or not according to a preset fluctuation interval and a numerical limit interval;

and if an invalid data point exists in the initial data set, replacing the value of the invalid data point with the value of a designated data point so as to update the initial data set to obtain target monitoring data.

3. The method of claim 1, wherein the validation processing of each data point in the initial data set to obtain target monitoring data comprises:

determining an initial data point from the initial data set according to a preset numerical limit interval;

judging whether a data point after the initial data point in the initial data set is an invalid data point or not according to a preset fluctuation interval, wherein if a judgment value determined by a current data point in the initial data set and a previous data point of the current data point is outside the preset fluctuation interval, the current data point is represented as an invalid data point, and if the judgment value determined by the current data point in the initial data set and the previous data point of the current data point is within the preset fluctuation interval, the current data point is represented as an effective data point;

and if an invalid data point exists in the initial data set, replacing the value of the invalid data point with the value of a designated data point so as to update the initial data set to obtain target monitoring data.

4. The method of claim 2 or 3, wherein replacing the value of the invalid data point with the value of the designated data point comprises:

replacing the value of the invalid data point with the value of a valid data point that is closest in time distance to the invalid data point; or,

and fitting an objective function according to the determined valid data points, and replacing the values of the invalid data points with the values in the objective function.

5. The method of claim 1, wherein the trend function is a function of time and a measured parameter; the extracting data from the variation trend function according to the set time sequence to form an initial data group comprises the following steps:

and extracting a plurality of data points with equal time distance from the variation trend function to form an initial data set.

6. The method according to claim 1, wherein the obtaining a variation trend function corresponding to the monitoring data according to the collected monitoring data of the monitored equipment comprises:

linearly connecting every two adjacent data points in the collected monitoring data to obtain a variation trend function comprising a piecewise linear function; or,

and performing curve fitting on each data point in the collected monitoring data to obtain a variation trend function.

7. The method of claim 1, further comprising:

determining a status score of the monitored equipment according to the target monitoring data;

and determining a target alarm signal according to the state score.

8. A monitoring data processing apparatus, comprising:

the obtaining module is used for obtaining a change trend function corresponding to the monitoring data according to the collected monitoring data of the monitored equipment;

the extraction module is used for extracting data from the change trend function according to a set time sequence to form an initial data set;

and the processing module is used for carrying out effectiveness processing on each data point in the initial data set so as to obtain target monitoring data.

9. An electronic device, comprising: a processor, a memory storing machine-readable instructions executable by the processor, the machine-readable instructions when executed by the processor performing the steps of the method of any of claims 1 to 7 when the electronic device is run.

10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, performs the steps of the method of any one of claims 1 to 7.

Images