CN114353881B - Equipment abnormity monitoring method and system based on composite sensor - Google Patents
Equipment abnormity monitoring method and system based on composite sensor Download PDFInfo
- Publication number
- CN114353881B CN114353881B CN202210268807.8A CN202210268807A CN114353881B CN 114353881 B CN114353881 B CN 114353881B CN 202210268807 A CN202210268807 A CN 202210268807A CN 114353881 B CN114353881 B CN 114353881B
- Authority
- CN
- China
- Prior art keywords
- monitoring
- data
- sequence
- multidimensional data
- calculating
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention provides a device abnormity monitoring method and system based on a composite sensor, which selects a plurality of points on a circuit of a device to be detected as monitoring points, respectively obtains multidimensional data on each monitoring point, selects a plurality of different moments as monitoring moments, respectively obtains the multidimensional data on each monitoring point at each monitoring moment to form a multidimensional data sequence, calculating to obtain the next monitoring time according to each monitoring time and the multidimensional data sequence, calculating to obtain a jump threshold according to the multidimensional data sequence, respectively obtaining multidimensional data on each monitoring point at the next monitoring time as to-be-detected multidimensional data, whether the multi-dimensional data to be detected is abnormal or not is calculated according to the jump threshold, so that the abnormity of the equipment is quickly positioned according to the multi-dimensional data at multiple moments, the threshold is dynamically calculated, and the accuracy of equipment abnormity detection is greatly improved.
Description
Technical Field
The disclosure belongs to the field of intelligent detection of physical property data, and particularly relates to an equipment abnormity monitoring method and system based on a composite sensor.
Background
The composite sensor can acquire the multidimensional data of the equipment to be detected in a multidimensional manner to perform data detection, the multidimensional data are composed of sound data, temperature data, vibration signals, voltage values and current values, and the abnormal state of the equipment can be efficiently identified by calculating and monitoring the multidimensional data acquired at different moments.
Disclosure of Invention
The present invention is directed to a method and system for monitoring device abnormalities based on a composite sensor, which solves one or more of the problems of the prior art and provides at least one of the advantages of the present invention.
The utility model provides a device abnormity monitoring method and system based on a composite sensor, a plurality of points are selected on a device to be detected as monitoring points, data are obtained on the monitoring points, multidimensional data are respectively obtained on each monitoring point, the multidimensional data are arrays composed of sound data, temperature data, vibration signals, voltage values and current values, a plurality of different moments are selected as monitoring moments, multidimensional data are respectively obtained on each monitoring point at each monitoring moment to form multidimensional data sequences, next monitoring moment is obtained through calculation according to each monitoring moment and the multidimensional data sequences, jump threshold values are obtained through calculation according to the multidimensional data sequences, multidimensional data are respectively obtained on each monitoring point at the next monitoring moment to serve as multidimensional data to be detected, and whether the multidimensional data to be detected have abnormity is calculated according to the jump threshold values.
In order to achieve the above object, according to an aspect of the present disclosure, there is provided a device abnormality monitoring method based on a composite sensor, the method including the steps of:
s100, selecting a plurality of points on equipment to be detected as monitoring points, and acquiring data from the monitoring points;
s200, respectively obtaining multidimensional data on each monitoring point, wherein the multidimensional data are an array consisting of sound data, temperature data, vibration signals, voltage values and current values;
s300, selecting a plurality of different moments as monitoring moments, and respectively obtaining multidimensional data on each monitoring point at each monitoring moment to form a multidimensional data sequence;
s400, calculating to obtain the next monitoring time according to each monitoring time and the multi-dimensional data sequence;
s500, calculating to obtain a jump threshold according to the multi-dimensional data sequence;
s600, acquiring multi-dimensional data on each monitoring point at the next monitoring moment as to-be-detected multi-dimensional data, and calculating whether the to-be-detected multi-dimensional data is abnormal or not according to a jump threshold.
Further, in S100, a device to be detected is obtained, a plurality of points are selected as monitoring points on the device to be detected, and a method for obtaining data on the monitoring points includes: the device to be detected is mechanical equipment which is connected with electricity and runs, the mechanical equipment at least comprises a numerical control machine, each point of a plurality of points is selected on a circuit of the device to be detected to serve as a monitoring point, data are obtained on each monitoring point, and the obtained data comprise sound data, temperature data, vibration signals, voltage values and current values.
Further, in S200, the method for respectively obtaining multi-dimensional data at each monitoring point, where the multi-dimensional data is an array composed of sound data, temperature data, vibration signal, voltage value, and current value specifically includes: acquiring a multi-dimensional data from all monitoring points at the same time, wherein the multi-dimensional data is an array consisting of sound data, temperature data, vibration signals, voltage values and current values; in the multi-dimensional data, since the circuit is also on the device under test, sound can be propagated through vibration of the wire on the whole device under test including the circuit thereof, sound data on the monitoring point represents vibration waves transmitted from the surroundings received at the monitoring point, the sound data is a value obtained by calculating an arithmetic mean of loudness values (in decibels) acquired by the sound volume detector and an arithmetic mean of frequency values (in hertz) acquired by the sound tester at each monitoring point, the arithmetic mean of the loudness values is d, the arithmetic mean of the frequency values is f, the sound data is vo, and the calculation formula of vo =0.618 x d + (1-0.618) f, thereby obtaining a value of the sound data as vo; in the multi-dimensional data, the temperature data is an arithmetic mean of values of temperatures (in degrees centigrade) at the monitoring points acquired by the temperature sensors at the respective monitoring points, the vibration signals are arithmetic means of values of accelerations (in m/s) acquired at the monitoring points by the triaxial acceleration sensors at the respective monitoring points, the voltage values are arithmetic means of values of voltages (in volts) of the points acquired at the monitoring points by the voltage sensors at the respective monitoring points, and the current values are arithmetic means of values of currents (in amperes) of the points acquired at the monitoring points by the current sensors at the respective monitoring points.
Further, in S300, a plurality of different moments are selected as monitoring moments, and a method for acquiring multidimensional data on each monitoring point at each monitoring moment to form a multidimensional data sequence includes:
recording the number of the selected multiple different monitoring moments as n, wherein the sequence number of each monitoring moment in time sequence is i, the monitoring moment with the sequence number of i is denoted as tim (i), i belongs to [1, n ], taking a sequence consisting of multi-dimensional data obtained at each monitoring moment as a multi-dimensional data sequence, wherein the number of elements in the multi-dimensional data sequence is correspondingly consistent with the number of the monitoring moments, the sequence number of the elements in the multi-dimensional data sequence is correspondingly consistent with the sequence number of the monitoring moments, the number of the elements in the multi-dimensional data sequence is also n, the sequence number of the elements in the multi-dimensional data sequence is also i, the multi-dimensional data sequence is denoted as Mulseq, the element with the sequence number of i in the multi-dimensional data sequence is denoted as Mulseq (i), the sound data in the Mulseq (i) is denoted as vo (i), the temperature data in the Mulseq (i) is denoted as t (i), and the vibration signal in the Mulseq (z (i), the voltage value in mulseq (i) is denoted by y (i), the current value in mulseq (i) is denoted by a (i), and mulseq (i) = [ vo (i), t (i), z (i), y (i), a (i) ] are sequentially provided, thereby obtaining the multidimensional data sequence.
Further, in S400, a method for calculating a next monitoring time according to each monitoring time and the multidimensional data sequence is as follows:
calculating the monitoring time steps of n monitoring times according to the n monitoring times, recording the monitoring time steps of the n monitoring times as pas (n), wherein the calculation formula of pas (n) is as follows:
where tim (i +1) -tim (i) denotes the interval of time between the monitoring instant tim (i) and its next monitoring instant tim (i + 1);
at the monitoring time (tim) (n) with the sequence number n, calculating the step proportion in n monitoring times according to the multidimensional data sequence, recording the step proportion in n monitoring times as pit (n), wherein the calculation formula of pit (n) is as follows:
wherein, the function f () is a step function, the step function is a function for calculating the amplitude of the variation between the values in the sequence or signal, and the calculation formula of f (vo) is:
the formula for f (t) is:
the formula for the calculation of (f), (z) is:
the formula for f (y) is:
the calculation formula of f (a) is:
the calculation process of the function Squd () specifically includes: in the function Squd (), the number of terms of the input numerical value input to the function Squd () is obtained as s, and the number of terms of the input numerical value, that is, the number of numerical values of how many terms are input to the function Squd (), is calculated to obtain (f (vo) f (t) f (z) f (y) f (a))pNumerical value of (1), the power of the sameThe calculation formula of the numerical values of the variables p and p is p = (s)/(s +1), so that the calculation result of the form (n) is the step proportion, and the step proportion in n monitoring moments is obtained through calculation, so that the beneficial effects that the monitoring is invalid due to the variable amplitude between the numerical values of uncertainty probability existing among the steps, and the abnormal condition of specific equipment cannot be detected if the probability of the amplitude between the steps is not accurately fitted, and the calculation method of the form (n) provides a high-speed low-time-consumption solution method for accurately fitting the probability of the amplitude between the steps, and the monitoring accuracy of the equipment is effectively guaranteed;
calculating the next monitoring time according to the monitoring time steps of the n monitoring times and the step proportion in the n monitoring times: and if the next monitoring time is the next monitoring time of the existing n monitoring times, recording the next monitoring time as tim (n +1), wherein the calculation formula of tim (n +1) is as follows:
tim (n) + fot (n) pas (n) indicates the time length of adding fot (n) pas (n) to tim (n) to obtain the next monitoring time.
Further, in S500, according to the multidimensional data sequence, the method for calculating the jump threshold value includes:
calculating an arithmetic mean of sound data in each of the multidimensional data in the multidimensional data sequence as vo (a),
calculating an arithmetic mean of the temperature data in each of the multidimensional data in the sequence of multidimensional data as t (a),
calculating an arithmetic mean of the vibration signals in each of the multi-dimensional data in the multi-dimensional data sequence as z (a),
calculating an arithmetic mean of voltage values in each of the multidimensional data in the sequence of multidimensional data as y (a),
calculating an arithmetic mean of current values in each of the multidimensional data in the sequence of multidimensional data as a (a),
the jump threshold is an array consisting of a sound data threshold, a temperature data threshold, a vibration signal threshold, a voltage threshold and a current threshold, and is recorded as an array Mulimit, wherein the sound data threshold is recorded as vo (li), the temperature data threshold is recorded as t (li), the vibration signal threshold is recorded as z (li), the voltage threshold is recorded as y (li) and the current threshold is recorded as a (li);
here, vo (li) = vo (a) × fot (n), t (li) = t (a) × fot (n), z (li) = z (a) × fot (n), y (li) = y (a) = fot (n), and a (li) = a (a) × fot (n), thereby obtaining the skip threshold value.
Further, in S600, at the next monitoring time, the multidimensional data is obtained at each monitoring point as the multidimensional data to be detected, and the method for calculating whether the multidimensional data to be detected is abnormal according to the jump threshold includes:
at the next monitoring time tim (n +1), acquiring one multi-dimensional data from all monitoring points at the monitoring time tim (n +1) as multi-dimensional data to be detected, recording the multi-dimensional data as Mulseq (n +1), recording sound data in the Mulseq (n +1) as vo (n +1), recording temperature data in the Mulseq (n +1) as t (n +1), recording vibration signals in the Mulseq (n +1) as z (n +1), recording voltage values in the Mulseq (n +1) as y (n +1), recording current values in the Mulseq (n +1) as a (n +1), and further judging whether a first constraint condition is met, wherein the first constraint condition is that any item of vo (n +1) > vo (li), (li) or t (n +1) > t (li), (li) or z (n +1) > z (li) or y (n +1) > y (li) or more than a (i) (a) or more than a (i) is met, and if the first constraint condition is met, the multi-dimensional data to be detected is abnormal, and the abnormal information at the monitoring time tim (n +1) is output through the output equipment of the computer.
The present disclosure also provides a device anomaly monitoring system based on a composite sensor, which includes: the device abnormality monitoring system based on the composite sensor can be operated in computing devices such as desktop computers, notebook computers, palm computers, cloud data centers and the like, and can be operated by including but not limited to a processor, a memory and a server cluster, and the processor executes the computer program to operate in the following units of the system:
the monitoring point data acquisition unit is used for selecting a plurality of points on the equipment to be detected as monitoring points and acquiring data from the monitoring points;
the multi-dimensional data acquisition unit is used for acquiring multi-dimensional data on each monitoring point respectively, and the multi-dimensional data is an array consisting of sound data, temperature data, vibration signals, voltage values and current values;
the multidimensional data sequence acquisition unit is used for selecting a plurality of different moments as monitoring moments and acquiring multidimensional data on each monitoring point at each monitoring moment to form a multidimensional data sequence;
the next monitoring time calculating unit is used for calculating to obtain the next monitoring time according to each monitoring time and the multi-dimensional data sequence;
the jump threshold calculation unit is used for calculating to obtain a jump threshold according to the multi-dimensional data sequence;
and the anomaly detection unit is used for respectively acquiring the multi-dimensional data on each monitoring point at the next monitoring moment as the multi-dimensional data to be detected, and calculating whether the multi-dimensional data to be detected is abnormal or not according to the jump threshold.
The beneficial effect of this disclosure does: the invention provides an equipment abnormity monitoring method and system based on a composite sensor, wherein a plurality of points are selected on equipment to be detected as monitoring points, data are acquired on the monitoring points, multidimensional data are acquired on each monitoring point respectively, the multidimensional data are arrays consisting of sound data, temperature data, vibration signals, voltage values and current values, a plurality of different moments are selected as monitoring moments, multidimensional data are acquired on each monitoring point at each monitoring moment respectively to form multidimensional data sequences, next monitoring moment is obtained through calculation according to each monitoring moment and the multidimensional data sequences, jump threshold values are obtained through calculation according to the multidimensional data sequences, multidimensional data are acquired on each monitoring point at the next monitoring moment respectively to serve as multidimensional data to be detected, whether the multidimensional data to be detected have abnormity is calculated according to the jump threshold values, and the abnormity of the equipment is rapidly positioned according to the multidimensional data at multiple moments, the threshold value is obtained through dynamic calculation, and the beneficial effect of greatly improving the accuracy of equipment abnormity detection is achieved.
Drawings
The foregoing and other features of the present disclosure will become more apparent from the detailed description of the embodiments shown in conjunction with the drawings in which like reference characters designate the same or similar elements throughout the several views, and it is apparent that the drawings in the following description are merely some examples of the present disclosure and that other drawings may be derived therefrom by those skilled in the art without the benefit of any inventive faculty, and in which:
FIG. 1 is a flow chart of a method for monitoring equipment anomalies based on a composite sensor;
fig. 2 is a system structure diagram of a device abnormality monitoring system based on a composite sensor.
Detailed Description
The conception, specific structure and technical effects of the present disclosure will be clearly and completely described below in conjunction with the embodiments and the accompanying drawings to fully understand the objects, aspects and effects of the present disclosure. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
Fig. 1 is a flow chart of a method for monitoring device abnormality based on a composite sensor according to the present invention, and a method and a system for monitoring device abnormality based on a composite sensor according to an embodiment of the present invention are described below with reference to fig. 1.
The present disclosure provides a device anomaly monitoring method based on a composite sensor, which specifically includes the following steps:
s100, selecting a plurality of points on equipment to be detected as monitoring points, and acquiring data from the monitoring points;
s200, respectively obtaining multidimensional data on each monitoring point, wherein the multidimensional data are an array consisting of sound data, temperature data, vibration signals, voltage values and current values;
s300, selecting a plurality of different moments as monitoring moments, and respectively obtaining multidimensional data on each monitoring point at each monitoring moment to form a multidimensional data sequence;
s400, calculating to obtain the next monitoring time according to each monitoring time and the multi-dimensional data sequence;
s500, calculating to obtain a jump threshold according to the multi-dimensional data sequence;
s600, acquiring multi-dimensional data on each monitoring point at the next monitoring moment as to-be-detected multi-dimensional data, and calculating whether the to-be-detected multi-dimensional data is abnormal or not according to a jump threshold.
Further, in S100, a device to be detected is obtained, a plurality of points are selected as monitoring points on the device to be detected, and a method for obtaining data on the monitoring points includes: the device to be detected is mechanical equipment which is electrified and runs, the mechanical equipment comprises any one or more of engineering machinery, a numerical control machine tool, electrical machinery and a machine tool, each of a plurality of points is selected on a circuit of the device to be detected to serve as a monitoring point, and data are acquired at each monitoring point.
Further, in S200, the method for respectively obtaining multi-dimensional data at each monitoring point, where the multi-dimensional data is an array composed of sound data, temperature data, vibration signal, voltage value, and current value specifically includes: acquiring a multi-dimensional data from all monitoring points at the same time, wherein the multi-dimensional data is an array consisting of sound data, temperature data, vibration signals, voltage values and current values; in the multidimensional data, the sound data is a value obtained by calculating an arithmetic mean of loudness values (in decibels) obtained by a volume detector and an arithmetic mean of frequency values (in hertz) obtained by a sound tester at each monitoring point, the arithmetic mean of the loudness values is d, the arithmetic mean of the frequency values is f, the sound data is vo, and the calculation formula of vo =0.618 d + (1-0.618) f, thereby obtaining a value of vo of the sound data; in the multi-dimensional data, the temperature data is an arithmetic mean of values of temperatures (in degrees centigrade) at the monitoring points acquired by the temperature sensors at the respective monitoring points, the vibration signal is an arithmetic mean of values of accelerations (in m/s) acquired at the monitoring points by the triaxial acceleration sensors at the respective monitoring points, the voltage value is an arithmetic mean of values of voltages (in volts) at the points acquired at the monitoring points by the voltage sensors at the respective monitoring points, and the current value is an arithmetic mean of values of currents (in amperes) at the points acquired at the monitoring points by the current sensors at the respective monitoring points.
Further, in S300, a plurality of different moments are selected as monitoring moments, and a method for acquiring multidimensional data on each monitoring point at each monitoring moment to form a multidimensional data sequence includes:
recording the number of the selected multiple different monitoring moments as n, wherein the sequence number of each monitoring moment in chronological order is i, the monitoring moment with the sequence number of i is denoted as tim (i), i belongs to [1, n ], using a sequence formed by the multidimensional data acquired at each monitoring moment as a multidimensional data sequence, wherein the number of elements in the multidimensional data sequence is correspondingly consistent with that of the monitoring moments, the sequence numbers of the elements in the multidimensional data sequence are correspondingly consistent with that of the monitoring moments, the number of the elements in the multidimensional data sequence is also n, the sequence numbers of the elements in the multidimensional data sequence are also i, the multidimensional data sequence is denoted as Mulseq, the element with the sequence number of i in the multidimensional data sequence is denoted as Mulseq (i), the sound data in the Mulseq (i) is denoted as vo (i), the temperature data in the Mulseq (i) is denoted as t (i), the vibration signal in the Mulseq (z) (i), the vibration signal sequence of the Mulseq (i) is denoted as, the voltage value in mulseq (i) is denoted by y (i), the current value in mulseq (i) is denoted by a (i), and mulseq (i) = [ vo (i), t (i), z (i), y (i), a (i) ] are sequentially provided, thereby obtaining the multidimensional data sequence.
Further, in S400, a method for calculating a next monitoring time according to each monitoring time and the multidimensional data sequence is as follows:
calculating the monitoring time steps of n monitoring times according to the n monitoring times, recording the monitoring time steps of the n monitoring times as pas (n), wherein the calculation formula of pas (n) is as follows:
where tim (i +1) -tim (i) denotes the interval of time between the monitoring instant tim (i) and its next monitoring instant tim (i + 1);
at the monitoring time (tim) (n) with the sequence number n, calculating the step proportion in n monitoring times according to the multidimensional data sequence, recording the step proportion in n monitoring times as pit (n), wherein the calculation formula of pit (n) is as follows:
wherein, the function f () is a step function, the step function is a function for calculating the amplitude of the variation between the values in the sequence or signal, and the calculation formula of f (vo) is:
the formula for f (t) is:
the formula for the calculation of (f), (z) is:
the formula for f (y) is:
the calculation formula of f (a) is:
the calculation process of the function Squd () specifically includes obtaining the number s of the calculation results of the step function input to the function Squd (), and calculating to obtain s = (f (vo) f (t) f (z) f (y) f (a))pThe power number is a variable p, and the calculation formula of the value of p is p = (s)/(s +1), so that the calculation result of fot (n) is the step ratio;
calculating the next monitoring time according to the monitoring time steps at the n monitoring times and the step proportion in the n monitoring times: and if the next monitoring time is the next monitoring time of the existing n monitoring times, recording the next monitoring time as tim (n +1), wherein the calculation formula of tim (n +1) is as follows:
tim (n) + fot (n) pas (n) indicates the time length of fot (n) pas (n) added to tim (n) to obtain the next monitoring time.
Further, in S500, according to the multidimensional data sequence, the method for calculating the jump threshold value includes:
calculating an arithmetic mean of sound data in each of the multidimensional data in the multidimensional data sequence as vo (a),
calculating an arithmetic mean of the temperature data in each of the multidimensional data in the sequence of multidimensional data as t (a),
calculating an arithmetic mean of the vibration signal in each of the multidimensional data in the sequence of multidimensional data as z (a),
calculating an arithmetic mean of voltage values in each of the multidimensional data in the sequence of multidimensional data as y (a),
calculating an arithmetic mean of current values in each of the multidimensional data in the multidimensional data sequence as a (a),
the jump threshold is an array consisting of a sound data threshold, a temperature data threshold, a vibration signal threshold, a voltage threshold and a current threshold, and is recorded as an array Mulimit, wherein the sound data threshold is recorded as vo (li), the temperature data threshold is recorded as t (li), the vibration signal threshold is recorded as z (li), the voltage threshold is recorded as y (li) and the current threshold is recorded as a (li);
here, vo (li) = vo (a) × fot (n), t (li) = t (a) × fot (n), z (li) = z (a) × fot (n), y (li) = y (a) = fot (n), and a (li) = a (a) × fot (n), thereby obtaining the skip threshold value.
Further, in S600, at the next monitoring time, obtaining multidimensional data as to-be-detected multidimensional data at each monitoring point, and calculating whether the to-be-detected multidimensional data is abnormal according to the jump threshold value, the method includes:
at the next monitoring time tim (n +1), acquiring one multi-dimensional data from all monitoring points at the monitoring time tim (n +1) as multi-dimensional data to be detected, recording the multi-dimensional data as Mulseq (n +1), recording sound data in the Mulseq (n +1) as vo (n +1), recording temperature data in the Mulseq (n +1) as t (n +1), recording vibration signals in the Mulseq (n +1) as z (n +1), recording voltage values in the Mulseq (n +1) as y (n +1), recording current values in the Mulseq (n +1) as a (n +1), and further judging whether a first constraint condition is met, wherein the first constraint condition is that any item of vo (n +1) > vo (li), (li) or t (n +1) > t (li), (li) or z (n +1) > z (li) or y (n +1) > y (li) or more than a (i) (a) or more than a (i) is met, and if the first constraint condition is met, the multi-dimensional data to be detected is abnormal, and the abnormal information at the monitoring time tim (n +1) is output through the output equipment of the computer.
The equipment abnormity monitoring system based on the compound sensor comprises: the device abnormality monitoring system based on the composite sensor can be operated in computing devices such as desktop computers, notebook computers, palm computers, cloud data centers and the like, and the operable systems can include, but are not limited to, processors, memories and server clusters.
As shown in fig. 2, the device abnormality monitoring system based on a composite sensor according to an embodiment of the present disclosure includes: a processor, a memory and a computer program stored in the memory and operable on the processor, the processor implementing the steps in one of the above-mentioned embodiments of the method for monitoring device anomalies based on composite sensors, the processor executing the computer program to operate in the units of the following system:
the monitoring point data acquisition unit is used for selecting a plurality of points on the equipment to be detected as monitoring points and acquiring data from the monitoring points;
the multi-dimensional data acquisition unit is used for acquiring multi-dimensional data on each monitoring point, and the multi-dimensional data is an array consisting of sound data, temperature data, vibration signals, voltage values and current values;
the multidimensional data sequence acquisition unit is used for selecting a plurality of different moments as monitoring moments and acquiring multidimensional data on each monitoring point at each monitoring moment to form a multidimensional data sequence;
the next monitoring time calculating unit is used for calculating to obtain the next monitoring time according to each monitoring time and the multi-dimensional data sequence;
the jump threshold calculation unit is used for calculating to obtain a jump threshold according to the multi-dimensional data sequence;
and the anomaly detection unit is used for respectively acquiring the multi-dimensional data on each monitoring point at the next monitoring moment as the multi-dimensional data to be detected, and calculating whether the multi-dimensional data to be detected is abnormal or not according to the jump threshold.
The equipment abnormity monitoring system based on the composite sensor can be operated in computing equipment such as desktop computers, notebook computers, palm computers and cloud data centers. The device abnormality monitoring system based on the composite sensor comprises a processor and a memory. Those skilled in the art will appreciate that the example is only an example of the device abnormality monitoring method and system based on the composite sensor, and does not constitute a limitation of the device abnormality monitoring method and system based on the composite sensor, and may include more or less components than the composite sensor, or combine some components, or different components, for example, the device abnormality monitoring system based on the composite sensor may further include an input/output device, a network access device, a bus, and the like.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete component Gate or transistor logic, discrete hardware components, etc. The general processor can be a microprocessor or the processor can be any conventional processor and the like, the processor is a control center of the equipment abnormality monitoring system based on the composite sensor, and various interfaces and lines are utilized to connect various subareas of the whole equipment abnormality monitoring system based on the composite sensor.
The memory may be used to store the computer programs and/or modules, and the processor may implement the various functions of the complex sensor based device anomaly monitoring method and system by running or executing the computer programs and/or modules stored in the memory and calling the data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The invention provides an equipment abnormity monitoring method and system based on a composite sensor, wherein a plurality of points are selected on equipment to be detected as monitoring points, data are obtained on the monitoring points, multidimensional data are respectively obtained on each monitoring point, the multidimensional data are arrays consisting of sound data, temperature data, vibration signals, voltage values and current values, a plurality of different moments are selected as monitoring moments, multidimensional data are respectively obtained on each monitoring point at each monitoring moment to form a multidimensional data sequence, the next monitoring moment is obtained through calculation according to each monitoring moment and the multidimensional data sequence, a jump threshold value is obtained through calculation according to the multidimensional data sequence, the multidimensional data are respectively obtained on each monitoring point at the next monitoring moment as the multidimensional data to be detected, whether the multidimensional data to be detected are abnormal or not is calculated according to the jump threshold value, and the equipment abnormity is quickly positioned according to the multidimensional data at the moments, the threshold value is obtained through dynamic calculation, and the beneficial effect of greatly improving the accuracy of equipment abnormity detection is achieved.
Although the description of the present disclosure has been rather exhaustive and particularly described with respect to several illustrated embodiments, it is not intended to be limited to any such details or embodiments or any particular embodiments, so as to effectively encompass the intended scope of the present disclosure. Furthermore, the foregoing describes the disclosure in terms of embodiments foreseen by the inventor for which an enabling description was available, notwithstanding that insubstantial modifications of the disclosure, not presently foreseen, may nonetheless represent equivalent modifications thereto.
Claims (4)
1. A device abnormality monitoring method based on a composite sensor is characterized by comprising the following steps:
s100, selecting a plurality of points on equipment to be detected as monitoring points, and acquiring data from the monitoring points;
s200, respectively obtaining multidimensional data on each monitoring point, wherein the multidimensional data are an array consisting of sound data, temperature data, vibration signals, voltage values and current values;
s300, selecting a plurality of different moments as monitoring moments, and respectively obtaining multidimensional data on each monitoring point at each monitoring moment to form a multidimensional data sequence;
s400, calculating to obtain the next monitoring time according to each monitoring time and the multidimensional data sequence;
s500, calculating to obtain a jump threshold according to the multi-dimensional data sequence;
s600, acquiring multi-dimensional data on each monitoring point at the next monitoring moment as to-be-detected multi-dimensional data, and calculating whether the to-be-detected multi-dimensional data is abnormal or not according to a jump threshold;
in S200, the method for respectively obtaining multidimensional data at each monitoring point, where the multidimensional data is an array of sound data, temperature data, a vibration signal, a voltage value, and a current value specifically includes: acquiring a multi-dimensional data from all monitoring points at the same time, wherein the multi-dimensional data is an array consisting of sound data, temperature data, vibration signals, voltage values and current values; in the multidimensional data, the sound data is a value obtained by calculating an arithmetic mean of loudness values obtained by the sound volume detector and an arithmetic mean of frequency values obtained by the sound tester at each monitoring point, the arithmetic mean of the loudness values is denoted as d, the arithmetic mean of the frequency values is denoted as f, the sound data is denoted as vo, and the calculation formula of vo is vo =0.618 d + (1-0.618) f, thereby obtaining a value of the sound data as vo; in the multi-dimensional data, the temperature data is an arithmetic mean of values of temperatures at the monitoring points acquired by the temperature sensors at the respective monitoring points, the vibration signal is an arithmetic mean of values of accelerations acquired at the monitoring points by the three-axis acceleration sensors at the respective monitoring points, the voltage value is an arithmetic mean of values of voltages at the monitoring points acquired at the monitoring points by the voltage sensors at the respective monitoring points, and the current value is an arithmetic mean of values of currents at the monitoring points acquired at the monitoring points by the current sensors at the respective monitoring points;
in S300, a plurality of different moments are selected as monitoring moments, and the method of obtaining multidimensional data on each monitoring point at each monitoring moment to form a multidimensional data sequence includes:
recording the number of the selected multiple different monitoring moments as n, wherein the sequence number of each monitoring moment in time sequence is i, the monitoring moment with the sequence number of i is denoted as tim (i), i belongs to [1, n ], taking a sequence consisting of multi-dimensional data obtained at each monitoring moment as a multi-dimensional data sequence, wherein the number of elements in the multi-dimensional data sequence is correspondingly consistent with the number of the monitoring moments, the sequence number of the elements in the multi-dimensional data sequence is correspondingly consistent with the sequence number of the monitoring moments, the number of the elements in the multi-dimensional data sequence is also n, the sequence number of the elements in the multi-dimensional data sequence is also i, the multi-dimensional data sequence is denoted as Mulseq, the element with the sequence number of i in the multi-dimensional data sequence is denoted as Mulseq (i), the sound data in the Mulseq (i) is denoted as vo (i), the temperature data in the Mulseq (i) is denoted as t (i), and the vibration signal in the Mulseq (z (i), voltage values in the Mulseq (i) are denoted by y (i), current values in the Mulseq (i) are denoted by a (i), and Mulseq (i) = [ vo (i), t (i), z (i), y (i), a (i) ] are sequentially arranged, so that a multidimensional data sequence is obtained;
in S400, the method for calculating the next monitoring time according to each monitoring time and the multidimensional data sequence includes:
calculating the monitoring time steps of n monitoring times according to the n monitoring times, recording the monitoring time steps of the n monitoring times as pas (n), wherein the calculation formula of pas (n) is as follows:
wherein, tim (i +1) -tim (i) represents the interval of time between monitoring time tim (i) and its next monitoring time tim (i + 1);
at the monitoring time (tim) (n) with the sequence number n, calculating the step proportion in n monitoring times according to the multidimensional data sequence, recording the step proportion in n monitoring times as pit (n), wherein the calculation formula of pit (n) is as follows:
wherein, the function f () is a step function, the step function is a function for calculating the amplitude of the variation between the values in the sequence or signal, and the calculation formula of f (vo) is:
the formula for f (t) is:
the formula for the calculation of (f), (z) is:
the formula for f (y) is:
the calculation formula of f (a) is:
the calculation process of the function Squd () specifically includes: in the function Squd (), the input is obtainedThe number of terms of the input numerical value to the function Squd () is s, and the number of terms of the input numerical value, that is, the number of numerical values of how many terms are input to the function Squd (), is calculated to obtain (f (vo) f (t) (z) f (y) f (a))pThe power number is a variable p, and the calculation formula of the value of p is p = (s)/(s +1), so that the calculation result of fot (n) is the step ratio;
calculating the next monitoring moment according to the steps of the n monitoring moments and the step proportion in the n monitoring moments: if the latter monitoring time is the latter monitoring time of the existing n monitoring times, then the latter monitoring time is recorded as tim (n +1), and the calculation formula of tim (n +1) is:
tim (n) + fot (n) pas (n) shows the time length of fot (n) pas (n) added to tim (n) to obtain the next monitoring time;
in S500, according to the multidimensional data sequence, the method for calculating the jump threshold includes:
calculating an arithmetic mean of sound data in each of the multidimensional data in the multidimensional data sequence as vo (a),
calculating an arithmetic mean of the temperature data in each of the multidimensional data in the sequence of multidimensional data as t (a),
calculating an arithmetic mean of the vibration signal in each of the multidimensional data in the sequence of multidimensional data as z (a),
calculating an arithmetic mean of voltage values in each of the multidimensional data in the sequence of multidimensional data as y (a),
calculating an arithmetic mean of current values in each of the multidimensional data in the multidimensional data sequence as a (a),
the jump threshold is an array consisting of a sound data threshold, a temperature data threshold, a vibration signal threshold, a voltage threshold and a current threshold, and is recorded as an array Mulimit, wherein the sound data threshold is recorded as vo (li), the temperature data threshold is recorded as t (li), the vibration signal threshold is recorded as z (li), the voltage threshold is recorded as y (li) and the current threshold is recorded as a (li);
wherein, vo (li) = vo (a) × fot (n), t (li) = t (a) × fot (n), z (li) = z (a) × fot (n), y (li) = y (a) = fot (n), and a (li) = a (a) × fot (n), thereby obtaining the skip threshold value;
and acquiring one multi-dimensional data from all monitoring points at the later monitoring time tim (n +1) to be used as the multi-dimensional data to be detected and recording the multi-dimensional data as Mulseq (n + 1).
2. The method for monitoring the abnormality of the equipment based on the composite sensor as claimed in claim 1, wherein in S100, the equipment to be detected is obtained, a plurality of points are selected on the equipment to be detected as monitoring points, and the method for obtaining data on the monitoring points comprises: the device to be detected is mechanical equipment which is connected with electricity and in operation, each point of a plurality of points is selected on a circuit of the device to be detected to serve as a monitoring point, and data are obtained on each monitoring point.
3. The method for monitoring equipment abnormality based on composite sensor according to claim 1, wherein in S600, at the later monitoring time, the multidimensional data is obtained at each monitoring point as the multidimensional data to be detected, and the method for calculating whether the multidimensional data to be detected is abnormal or not according to the jump threshold value is as follows:
sound data in Mulseq (n +1) is denoted vo (n +1), temperature data in Mulseq (n +1) is denoted t (n +1), vibration signal in Mulseq (n +1) is denoted z (n +1), voltage value in Mulseq (n +1) is denoted y (n +1), current value in Mulseq (n +1) is denoted a (n +1), further determining whether a first constraint condition is satisfied, the first constraint condition being any one or more of vo (n +1) > vo (li) or t (n +1) > t (li) or z (n +1) > z (li) or y (n +1) > y (li) or a (n +1) > a (i), if the first constraint condition is satisfied, and outputting the abnormal information of the monitoring time tim (n +1) through the output equipment of the computer.
4. A composite sensor-based equipment anomaly monitoring system is characterized by comprising: a processor, a memory and a computer program stored in the memory and running on the processor, the processor implementing the steps of the method for monitoring equipment abnormality based on a composite sensor according to any one of claims 1 to 3 when executing the computer program, the system for monitoring equipment abnormality based on a composite sensor being run in computing equipment of desktop computers, notebook computers, palm computers and cloud data centers.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210268807.8A CN114353881B (en) | 2022-03-18 | 2022-03-18 | Equipment abnormity monitoring method and system based on composite sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210268807.8A CN114353881B (en) | 2022-03-18 | 2022-03-18 | Equipment abnormity monitoring method and system based on composite sensor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114353881A CN114353881A (en) | 2022-04-15 |
| CN114353881B true CN114353881B (en) | 2022-06-24 |
Family
ID=81095248
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210268807.8A Active CN114353881B (en) | 2022-03-18 | 2022-03-18 | Equipment abnormity monitoring method and system based on composite sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114353881B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115098475B (en) * | 2022-06-22 | 2024-03-19 | 深圳亿嘉和科技研发有限公司 | Inspection robot battery abnormal data recording method based on secondary screening |
| CN115187155B (en) * | 2022-09-15 | 2022-12-27 | 广东银纳增材制造技术有限公司 | School laboratory equipment state data control method |
| CN115980281B (en) * | 2023-03-16 | 2023-07-18 | 深圳奥雅设计股份有限公司 | Carbon source detection method and system based on carbon neutralization |
| CN116111731B (en) * | 2023-04-13 | 2023-06-20 | 东莞先知大数据有限公司 | Distributed energy storage equipment abnormality determination method, device, equipment and medium |
| CN116414097B (en) * | 2023-05-15 | 2023-09-29 | 广东思创智联科技股份有限公司 | Alarm management method and system based on industrial equipment data |
| CN116859831B (en) * | 2023-05-15 | 2024-01-26 | 广东思创智联科技股份有限公司 | Industrial big data processing method and system based on Internet of things |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2017204107A (en) * | 2016-05-11 | 2017-11-16 | 株式会社日立製作所 | Data analytic method, and system and device therefor |
| CN106640688B (en) * | 2016-12-05 | 2019-04-16 | 中国石油集团川庆钻探工程有限公司工程技术研究院 | A kind of intelligent diagnosis system and method for output pump unit on-line monitoring failure |
| CN107132064B (en) * | 2017-05-17 | 2019-02-26 | 山东大学 | Rotatory mechanical system method for monitoring operation states and system based on multisensor |
| CN110147902A (en) * | 2019-04-10 | 2019-08-20 | 焦点科技股份有限公司 | A kind of multinomial operation indicator joint method for monitoring abnormality |
| CN110942137A (en) * | 2019-10-18 | 2020-03-31 | 云南电网有限责任公司信息中心 | Power grid information operation and maintenance monitoring method based on deep learning |
| CN111082518A (en) * | 2019-11-18 | 2020-04-28 | 中国电力企业联合会电力建设技术经济咨询中心 | Power grid operation fault monitoring system based on multidimensional data |
| CN211373701U (en) * | 2020-01-20 | 2020-08-28 | 江苏智冷物联技术有限公司 | Composite sensor |
| CN112288126B (en) * | 2020-09-09 | 2022-06-17 | 广东石油化工学院 | Sampling data abnormal change online monitoring and diagnosing method |
| CN112990442B (en) * | 2021-04-21 | 2021-08-06 | 北京瑞莱智慧科技有限公司 | Data determination method and device based on spatial position and electronic equipment |
-
2022
- 2022-03-18 CN CN202210268807.8A patent/CN114353881B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114353881A (en) | 2022-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114353881B (en) | Equipment abnormity monitoring method and system based on composite sensor | |
| CN112270312B (en) | Fan bearing fault diagnosis method, system, computer equipment and storage medium | |
| CN110213258B (en) | Abnormity monitoring method and device for vehicle CAN bus and computer equipment | |
| JP2018077779A (en) | Sensor interface apparatus, measurement information communication system, measurement information communication method, and measurement information communication program | |
| CN110672325A (en) | Bearing working condition stability evaluation method and device based on probability distribution | |
| EP3795975A1 (en) | Abnormality sensing apparatus, abnormality sensing method, and abnormality sensing program | |
| CN117890776A (en) | Chip for monitoring motor performance and performance monitoring system of rotating equipment | |
| CN113902121A (en) | Method, device, equipment and medium for checking battery degradation presumption device | |
| CN112881052B (en) | Method and device for constructing working scene of mobile robot | |
| CN116974268B (en) | Intelligent monitoring and early warning method for control system circuit | |
| US10839258B2 (en) | Computer-readable recording medium, detection method, and detection device | |
| Chen et al. | Performance degradation assessment of rotary machinery based on a multiscale Tsallis permutation entropy method | |
| Hasan et al. | Machine learning-based sensor drift fault classification using discrete cosine transform | |
| CN115406652A (en) | Motor bearing fault diagnosis method, motor controller and readable storage medium | |
| CN110702408A (en) | Bearing state change event monitoring method and device | |
| CN112767379A (en) | Method, system and computer readable storage medium for fault detection in ceramic manufacturing | |
| CN111614318A (en) | Method and device for detecting direct-current side current fault of photovoltaic system | |
| CN117054903B (en) | Method and system for monitoring abnormality of automobile battery pack | |
| CN114528907B (en) | Industrial abnormal data detection method and device | |
| CN112130057B (en) | Radiation effect diagnosis system based on memristor neural network | |
| US20210133097A1 (en) | Signal collection method and signal collection device | |
| CN117851214A (en) | Test method of predictive control model and related equipment | |
| CN118625197A (en) | Battery fault diagnosis method, apparatus, device, storage medium, and program product | |
| CN116124459A (en) | Bearing fault diagnosis method, device, computer equipment and storage medium | |
| US20130154662A1 (en) | Testing system and method for electronic device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |