CN117786464B - Abnormality early warning method and system for electric heating constant temperature incubator - Google Patents
Abnormality early warning method and system for electric heating constant temperature incubator Download PDFInfo
- Publication number
- CN117786464B CN117786464B CN202410194421.6A CN202410194421A CN117786464B CN 117786464 B CN117786464 B CN 117786464B CN 202410194421 A CN202410194421 A CN 202410194421A CN 117786464 B CN117786464 B CN 117786464B
- Authority
- CN
- China
- Prior art keywords
- temperature
- fluctuation
- sequence
- value
- moment
- 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
- 230000005856 abnormality Effects 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000005485 electric heating Methods 0.000 title claims abstract description 22
- 238000012937 correction Methods 0.000 claims abstract description 52
- 230000008859 change Effects 0.000 claims description 52
- 230000002159 abnormal effect Effects 0.000 claims description 38
- 238000012549 training Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 11
- 238000013145 classification model Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 244000005700 microbiome Species 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Landscapes
- Accommodation For Nursing Or Treatment Tables (AREA)
- Apparatus Associated With Microorganisms And Enzymes (AREA)
Abstract
The application relates to the technical field of incubator early warning, in particular to an abnormality early warning method and system of an electric heating incubator, wherein the abnormality early warning method comprises the following steps: acquiring average temperature values at all moments in a set time period, and constructing a temperature fluctuation sequence according to average temperature value difference values of adjacent moments; constructing a power supply parameter fluctuation sequence according to the power supply parameter difference values at adjacent moments, and correcting the temperature fluctuation sequence according to the power supply parameter fluctuation sequence to obtain a temperature correction fluctuation sequence; constructing a temperature global uniformity sequence based on the temperature value of the temperature sensor and the target temperature value; constructing a temperature local deviation value sequence according to the deviation of the temperature values between the temperature sensor and the adjacent sensors; and inputting the temperature global uniformity sequence, the temperature local deviation amount sequence and the temperature correction fluctuation sequence into an abnormality early warning model to output an abnormality early warning result. By the technical scheme, the accuracy of abnormality early warning can be improved.
Description
Technical Field
The application relates to the technical field of incubator early warning, in particular to an abnormality early warning method and system of an electric heating incubator.
Background
An electrothermal constant temperature incubator is a device used in fields of biological experiments, medical researches and the like, and has a main function of providing a constant temperature environment to promote the culture of organisms such as cells, microorganisms, flora and the like. In the use process of the electrothermal constant temperature incubator, whether the temperature is kept constant directly influences the culture result of organisms.
Currently, patent application document CN114756427a discloses an incubator, and a control method and system thereof, wherein the control method comprises: acquiring first temperature information according to a first temperature sensor, wherein the first temperature information is the external environment temperature; obtaining a second temperature information set according to the second temperature sensor module, wherein the second temperature information set comprises second temperature information at a plurality of different positions; determining a first temperature flow velocity field according to the first temperature information and a plurality of second temperature information; obtaining a predetermined temperature flow velocity field; and determining whether first early warning information is obtained according to the difference between the preset temperature flow velocity field and the first temperature flow velocity field, wherein the first early warning information is used for reminding the constant temperature cabinet that ash removal treatment is required.
However, the above method can determine the first temperature flow rate field according to the external environment temperature of the incubator and the second temperature information at a plurality of different positions inside the incubator, and further judge whether the incubator has temperature abnormality according to the difference between the first temperature flow rate field and the predetermined temperature flow rate field; however, the method ignores the influence of the power supply condition of the electric heating constant temperature incubator on the internal temperature of the incubator, so that the abnormal early warning result is inaccurate.
Disclosure of Invention
In order to solve the technical problems, the application provides an abnormality early warning method and system for an electric heating constant temperature incubator, which consider the influence of power supply parameters of the electric heating constant temperature incubator on the internal temperature of the incubator and improve the accuracy of abnormality early warning.
The first aspect of the application provides an abnormality early warning method for an electrothermal constant temperature incubator, wherein a plurality of temperature sensors are arranged in the incubator, the plurality of temperature sensors are distributed in an array, and the abnormality early warning method comprises the following steps: acquiring average temperature values of the plurality of temperature sensors at each moment in a set time period, and subtracting the average temperature value of the last adjacent moment from the average temperature value of each moment to obtain a temperature fluctuation sequence, wherein the set time period comprises the current moment and a set number of moments before the current moment; subtracting the power supply parameter value of the last adjacent moment from the power supply parameter value of each moment to obtain a power supply parameter fluctuation sequence in the set time period, wherein the power supply parameter values comprise a voltage value and a current value; constructing a temperature change model, and correcting the temperature fluctuation sequence according to the temperature change model and the power supply parameter fluctuation sequence to obtain a temperature correction fluctuation sequence, wherein the input of the temperature change model is power supply parameter fluctuation, and the output of the temperature change model is temperature change quantity caused by the power supply parameter fluctuation; calculating the global uniformity of the temperature at each moment based on the deviation between the temperature values of all the temperature sensors and the target temperature value to construct a global uniformity sequence of the temperature in the set time period; calculating the temperature gradient of each temperature sensor according to the deviation of the temperature value between one temperature sensor and the adjacent sensor at any time in the set time period, and taking the maximum value of the temperature gradient as the local temperature deviation value at any time to construct a local temperature deviation value sequence in the set time period; and inputting the temperature global uniformity sequence, the temperature local deviation amount sequence and the temperature correction fluctuation sequence into a trained abnormality early warning model to output an abnormality early warning result at the current moment.
In one embodiment, the power supply parameter fluctuation includes voltage value fluctuation and current value fluctuation, and the constructing the temperature change model includes: constructing a temperature change initial model, wherein the temperature change initial model meets the relation:
wherein, For current value fluctuation,/>For voltage value fluctuation,/>Is the highest power of current value fluctuation,/>For the fluctuation of the current value/>Current weight corresponding to power,/>For the fluctuation of the current value/>To the power of the two,/(I)Is the highest power of voltage value fluctuation,/>For the fluctuation of voltage value/>Voltage weight corresponding to power,/>For the fluctuation of voltage value/>To the power of the two,/(I)The temperature variation caused by the fluctuation of the power supply parameters is used; collecting a plurality of groups of training samples, wherein the training samples comprise power supply parameter fluctuation under the normal state of an electrothermal constant temperature incubator and temperature variation corresponding to the power supply parameter fluctuation; and fitting the temperature change initial model on the plurality of groups of training samples by using a least square method, and determining the values of all the voltage weights and all the current weights so as to obtain a temperature change model.
In one embodiment, correcting the temperature fluctuation sequence according to the temperature change model and the power supply parameter fluctuation sequence to obtain a temperature correction fluctuation sequence includes: for one moment in the set time period, acquiring power supply parameter fluctuation of the moment based on the power supply parameter fluctuation sequence, inputting the power supply parameter fluctuation into the temperature change model, and taking an output result as a temperature correction quantity of the moment; acquiring the temperature fluctuation at the moment based on the temperature fluctuation sequence, and subtracting the temperature correction amount at the moment from the temperature fluctuation at the moment to obtain the temperature correction fluctuation at the moment; and acquiring temperature correction fluctuation at all moments in the set time period, and arranging all the temperature correction fluctuation according to the sequence of the moments to obtain a temperature correction fluctuation sequence.
In one embodiment, the calculating the global uniformity of the temperature at each moment based on the deviations between the temperature values of all the temperature sensors and the target temperature value to construct the global uniformity sequence of the temperature within the set time period includes: collecting temperature values of the plurality of temperature sensors for a moment in a set time period; calculating the global uniformity of the temperature at the moment based on the deviation between the temperature values of all the temperature sensors and the target temperature value, wherein the global uniformity of the temperature at the moment meets the relation:
wherein, For the number of the plurality of temperature sensors,/>For time/>Time/>Temperature value of individual temperature sensor,/>For the target temperature value,/>For time/>Is a global uniformity of temperature; and calculating the global uniformity of the temperature at each moment in the set time period, and arranging all the global uniformity of the temperature according to the sequence of the moment to obtain a global uniformity sequence of the temperature.
In one embodiment, at any time within the set time period, calculating a temperature gradient of each temperature sensor according to a deviation of temperature values between one temperature sensor and an adjacent sensor, and taking a maximum value of the temperature gradient as a temperature local deviation amount at the any time includes: at any time within the set time period, all adjacent sensors of one temperature sensor are obtained, the temperature gradient of the temperature sensor is calculated based on the deviation of the temperature value between the temperature sensor and the adjacent sensors, and the temperature gradient of the temperature sensor meets the relation:
wherein, For contiguous sensor set, includingAll adjacent sensors of the individual temperature sensors,/>For time/>Time/>Temperature value of individual temperature sensor,/>For time/>Time/>The temperature value of each of the adjacent sensors,For/>Number of all adjacent sensors of each temperature sensor,/>For time/>Time/>A temperature gradient of the individual temperature sensors; and calculating the temperature gradients of all the temperature sensors at any moment, and taking the maximum value of the temperature gradients as the local deviation amount of the temperature at any moment.
In one embodiment, the anomaly early warning model includes a first timing model, a second timing model, a third timing model, and a classification model; the first time sequence model is used for extracting time sequence characteristics of the temperature global uniformity sequence to obtain temperature global uniformity characteristics; the second time sequence model is used for extracting time sequence characteristics of the temperature local deviation value sequence to obtain temperature local deviation value characteristics; the third time sequence model is used for extracting time sequence characteristics of the temperature correction fluctuation sequence to obtain temperature correction fluctuation characteristics; and inputting the temperature global uniformity characteristic, the temperature local deviation quantity characteristic and the temperature correction fluctuation characteristic into the classification model to output an abnormality early-warning result at the current moment, wherein the abnormality early-warning result comprises abnormality and normal.
In one embodiment, the training method of the anomaly early warning model includes: in the history use process of the electric heating constant temperature incubator, acquiring a temperature global uniformity sequence, a temperature local deviation amount sequence and a temperature correction fluctuation sequence of any set time period as input samples, and taking a use state at the last moment of the set time period as a sample label of the input samples, wherein the use state comprises abnormal and normal; inputting the input sample into the abnormal early warning model to obtain an output result; calculating a cross entropy loss function value based on the output result and a sample label of the input sample; performing back propagation according to the cross entropy loss function value, updating the abnormal early warning model, and completing one-time training; and iteratively training the abnormal early warning model until the cross entropy loss function value is smaller than a set loss value, and obtaining the trained abnormal early warning model.
In one embodiment, an early warning alert is issued in response to the current time of day abnormality alert result being an abnormality.
The application also provides an abnormality early warning system of the electrothermal incubator, which comprises a processor and a memory, wherein the memory stores computer program instructions, and the abnormality early warning method of the electrothermal incubator according to the first aspect of the application is realized when the computer program instructions are executed by the processor.
The technical scheme of the application has the following beneficial technical effects:
According to the technical scheme provided by the application, the temperature fluctuation sequence is obtained according to the change of the average temperature value between adjacent moments in the set time period, and further, the temperature fluctuation sequence is corrected according to the power supply parameter fluctuation sequence in consideration of the influence of power supply parameter fluctuation on the temperature fluctuation, so that the temperature correction fluctuation sequence is obtained, and the temperature correction fluctuation sequence can exclude the temperature change caused by the power supply parameter fluctuation and accurately reflect whether the electric heating constant temperature incubator is in an abnormal state or not; further, a temperature global uniformity sequence and a temperature local deviation amount sequence are acquired, wherein the temperature global uniformity sequence can reflect the temperature global uniformity at each moment in a set time period, and the temperature global uniformity can reflect the deviation between the temperature values at different positions and the target temperature value; the sequence of local temperature deviations can reflect a local temperature deviation amount for each location that can reflect a maximum value of the temperature deviations in the contiguous range of all locations; and finally, inputting the temperature global uniformity sequence, the temperature local deviation sequence and the temperature correction fluctuation sequence into a trained abnormal early warning model to output an abnormal early warning result at the current moment, so that the accuracy of the abnormal early warning is improved while the real-time early warning of the electric heating constant temperature incubator is realized.
Drawings
The above, as well as additional purposes, features, and advantages of exemplary embodiments of the present application will become readily apparent from the following detailed description when read in conjunction with the accompanying drawings. In the drawings, embodiments of the application are illustrated by way of example and not by way of limitation, and like reference numerals refer to similar or corresponding parts and in which:
FIG. 1 is a flow chart of an abnormality pre-warning method of an electrically heated incubator according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a distribution of a plurality of temperature sensors according to an embodiment of the application;
FIG. 3 is a schematic diagram of an anomaly early warning model according to an embodiment of the present application;
fig. 4 is a block diagram of an abnormality early warning system of an electrothermal incubator according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be understood that when the terms "first," "second," and the like are used in the claims, the specification and the drawings of the present application, they are used merely for distinguishing between different objects and not for describing a particular sequential order. The terms "comprises" and "comprising" when used in the specification and claims of the present application are taken to specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
According to a first aspect of the application, the application provides an abnormality early warning method of an electrothermal constant temperature incubator, which is used for carrying out real-time early warning on the abnormality of the electrothermal constant temperature incubator in the use process of the electrothermal constant temperature incubator. A plurality of temperature sensors are arranged in the electric heating constant temperature incubator and distributed in an array mode in the electric heating constant temperature incubator, and are used for collecting temperature values at different positions in the electric heating constant temperature incubator.
Fig. 1 is a flowchart of an abnormality early warning method of an electrothermal incubator according to an embodiment of the present application. As shown in fig. 1, the abnormality warning method 100 of the electrothermal incubator includes steps S101 to S106, which will be described in detail below.
S101, acquiring average temperature values of the plurality of temperature sensors at each moment in a set time period, and subtracting the average temperature value of the last adjacent moment from the average temperature value of each moment to obtain a temperature fluctuation sequence, wherein the set time period comprises the current moment and a set number of moments before the current moment.
In one embodiment, during the use of the electrothermal incubator, the current time and the time before the current time are taken as the set time period, for example, the set number is 15, and the current time and the 15 times before the current time form the set time period, that is, the set time includes 16 times; it can be understood that the set time period of the current time is used for obtaining the abnormal early warning result of the current time.
For a moment in a set period of timeTime/>The last adjacent instant of (a) is instant/>Will take time of dayTime/>The average temperature value of (a) to obtain time/>Is provided. And calculating the temperature fluctuation at each moment in the set time period according to the same method to obtain a temperature fluctuation sequence.
Thus, a temperature fluctuation sequence of a set time period is obtained, and the temperature fluctuation sequence can reflect the change condition of the overall temperature of the electric heating constant temperature incubator.
S102, subtracting the power supply parameter value of the last adjacent moment from the power supply parameter value of each moment to obtain a power supply parameter fluctuation sequence in the set time period, wherein the power supply parameter values comprise a voltage value and a current value.
In one embodiment, the power supply parameter value of the electrothermal incubator has a direct effect on the operation state of the electrothermal incubator, and when the power supply parameter value of the electrothermal incubator fluctuates, the temperature in the electrothermal incubator also fluctuates. In order to enable the temperature fluctuation sequence to accurately reflect whether the electric heating constant temperature incubator is in an abnormal state, the temperature fluctuation sequence needs to be corrected so as to remove the influence of fluctuation of the power supply parameter value on the temperature fluctuation sequence.
Acquiring a power supply parameter value of each moment in a set time period, for one moment in the set time periodTime/>The last adjacent instant of (a) is instant/>Time/>Time/>To obtain the time/>Is provided. And calculating power supply parameter fluctuation at each moment in the set time period according to the same method to obtain a power supply parameter fluctuation sequence, wherein the power supply parameter comprises a voltage value and a current value, and the power supply parameter fluctuation comprises a voltage value fluctuation and a current value fluctuation.
In this way, a power supply parameter fluctuation sequence is obtained, wherein the power supply parameter fluctuation sequence comprises power supply parameter fluctuation at each moment in a set time period, and the power supply parameter fluctuation sequence is subsequently used for correcting the temperature fluctuation sequence to remove the influence of fluctuation of power supply parameter values on the temperature fluctuation sequence.
S103, constructing a temperature change model, and correcting the temperature fluctuation sequence according to the temperature change model and the power supply parameter fluctuation sequence to obtain a temperature correction fluctuation sequence, wherein the input of the temperature change model is power supply parameter fluctuation, and the output of the temperature change model is temperature change quantity caused by the power supply parameter fluctuation.
In one embodiment, when the electrothermal incubator is in a normal state, the overall temperature in the electrothermal incubator also fluctuates along with the fluctuation of the power supply parameters; in order to enable the temperature fluctuation sequence to accurately reflect whether the electric heating constant temperature incubator is in an abnormal state, the temperature fluctuation sequence needs to be corrected according to the power supply parameter fluctuation sequence. And before the temperature fluctuation sequence is corrected according to the power supply parameter fluctuation sequence, a temperature change model is also required to be constructed.
Specifically, the power supply parameter fluctuation includes voltage value fluctuation and current value fluctuation, and the constructing the temperature change model includes: constructing a temperature change initial model, wherein the temperature change initial model meets the relation:
wherein, For current value fluctuation,/>For voltage value fluctuation,/>Is the highest power of current value fluctuation,/>For the fluctuation of the current value/>Current weight corresponding to power,/>For the fluctuation of the current value/>To the power of the two,/(I)Is the highest power of voltage value fluctuation,/>For the fluctuation of voltage value/>Voltage weight corresponding to power,/>For the fluctuation of voltage value/>To the power of the two,/(I)The temperature variation caused by the fluctuation of the power supply parameters is used; collecting a plurality of groups of training samples, wherein the training samples comprise power supply parameter fluctuation under the normal state of an electrothermal constant temperature incubator and temperature variation corresponding to the power supply parameter fluctuation; and fitting the temperature change initial model on the plurality of groups of training samples by using a least square method, and determining the values of all the voltage weights and all the current weights so as to obtain a temperature change model.
Wherein the highest power of the voltage value fluctuationAnd highest power of current value fluctuation/>The values of (2) are all 3.
In one embodiment, after the temperature change model is constructed, the temperature change amount caused by the power supply parameter wave can be determined according to the temperature change model, so that the temperature fluctuation sequence can be corrected. The specific description is as follows, the temperature fluctuation sequence is corrected according to the temperature change model and the power supply parameter fluctuation sequence, and the obtaining of the temperature correction fluctuation sequence comprises the following steps: for one moment in the set time period, acquiring power supply parameter fluctuation of the moment based on the power supply parameter fluctuation sequence, inputting the power supply parameter fluctuation into the temperature change model, and taking an output result as a temperature correction quantity of the moment; acquiring the temperature fluctuation at the moment based on the temperature fluctuation sequence, and subtracting the temperature correction amount at the moment from the temperature fluctuation at the moment to obtain the temperature correction fluctuation at the moment; and acquiring temperature correction fluctuation at all moments in the set time period, and arranging all the temperature correction fluctuation according to the sequence of the moments to obtain a temperature correction fluctuation sequence.
Exemplary, for the time within the set time periodTime/>, in a power supply parameter fluctuation sequenceCurrent value fluctuation of (2)0, Voltage value fluctuation/>1.6; Will/>And/>Inputting a temperature change model to obtain power supply parameter fluctuation/>AndThe amount of temperature change caused is expressed as/>; Time/>, in a temperature fluctuation sequenceTemperature fluctuation of (1)/(v)Obtaining the time/>, in the temperature correction fluctuation sequenceTemperature corrected fluctuations of (c).
In this way, the power supply parameter fluctuation at each moment in the power supply parameter fluctuation sequence is input into the temperature change model to obtain the temperature change quantity caused by the power supply parameter fluctuation, and the temperature fluctuation sequence is further corrected according to the temperature change quantity caused by the power supply parameter fluctuation to obtain the temperature correction fluctuation sequence, wherein the temperature correction fluctuation sequence can exclude the temperature change quantity caused by the power supply parameter fluctuation and accurately reflect whether the electric heating constant temperature incubator is in an abnormal state.
And S104, calculating the global uniformity of the temperature at each moment based on the deviation between the temperature values of all the temperature sensors and the target temperature value, so as to construct a global uniformity sequence of the temperature in the set time period.
In one embodiment, the temperature values of a plurality of temperature sensors can be acquired at the same time, and the temperature values of the temperature sensors can reflect the temperature values of different positions inside the electrothermal constant temperature incubator at the same time. In an ideal case, the temperatures of different positions inside the electrothermal constant temperature incubator should be equal to a target temperature value, wherein the target temperature value is a set temperature value of the electrothermal constant temperature incubator.
Specifically, the calculating the global uniformity of the temperature at each moment based on the deviations between the temperature values of all the temperature sensors and the target temperature value, so as to construct the global uniformity sequence of the temperature within the set time period includes: collecting temperature values of the plurality of temperature sensors for a moment in a set time period; calculating the global uniformity of the temperature at the moment based on the deviation between the temperature values of all the temperature sensors and the target temperature value, wherein the global uniformity of the temperature at the moment meets the relation:
wherein, For the number of the plurality of temperature sensors,/>For time/>Time/>Temperature value of individual temperature sensor,/>For the target temperature value,/>For time/>Is a global uniformity of temperature; and calculating the global uniformity of the temperature at each moment in the set time period, and arranging all the global uniformity of the temperature according to the sequence of the moment to obtain a global uniformity sequence of the temperature.
In this way, the temperature global uniformity sequence can reflect the temperature global uniformity at each moment in the set time period, and the temperature global uniformity can reflect the deviation between the temperature values at different positions and the target temperature value.
S105, calculating the temperature gradient of each temperature sensor according to the deviation of the temperature value between one temperature sensor and the adjacent sensor at any time in the set time period, and taking the maximum value of the temperature gradient as the local temperature deviation value at any time to construct a local temperature deviation value sequence in the set time period.
In one embodiment, the global uniformity sequence of temperature can reflect global uniformity of temperature at each moment in a set period of time, however, when global uniformity of temperature is large, it cannot be stated that temperatures in adjacent ranges of each position are uniform, and in order to accurately measure the relationship between temperature values at different positions at the same moment, it is also necessary to calculate the local deviation amount of temperature at each moment.
Specifically, at an arbitrary timing within the set period, calculating a temperature gradient of each temperature sensor from a deviation of temperature values between one temperature sensor and an adjacent sensor, and taking a maximum value of the temperature gradient as a temperature local deviation amount at the arbitrary timing includes: at any time within the set time period, all adjacent sensors of one temperature sensor are obtained, the temperature gradient of the temperature sensor is calculated based on the deviation of the temperature value between the temperature sensor and the adjacent sensors, and the temperature gradient of the temperature sensor meets the relation:
wherein, For contiguous sensor set, includingAll adjacent sensors of the individual temperature sensors,/>For time/>Time/>Temperature value of individual temperature sensor,/>For time/>Time/>The temperature value of each of the adjacent sensors,For/>Number of all adjacent sensors of each temperature sensor,/>For time/>Time/>A temperature gradient of the individual temperature sensors; and calculating the temperature gradients of all the temperature sensors at any moment, and taking the maximum value of the temperature gradients as the local deviation amount of the temperature at any moment. The larger the local deviation amount of the temperature is, the greater the possibility that the electrothermal incubator is in abnormality is.
Exemplary, please refer to fig. 2, which is a schematic diagram illustrating a distribution of a plurality of temperature sensors according to an embodiment of the present application. For the 3 rd temperature sensor, three adjacent sensors are respectively a2 nd temperature sensor, a5 th temperature sensor and a6 th temperature sensor; the three adjacent sensors also constitute the adjacent range of the 3 rd temperature sensor.
Calculating the local temperature deviation values at each moment in the set time period according to the same method, and arranging all the local temperature deviation values according to the sequence of the moments to obtain a local temperature deviation value sequence; the sequence of local temperature deviations can reflect a local temperature deviation for each location, which can reflect a maximum value of temperature deviations in contiguous ranges for all locations.
S106, inputting the temperature global uniformity sequence, the temperature local deviation amount sequence and the temperature correction fluctuation sequence into a trained abnormality early warning model to output an abnormality early warning result at the current moment.
In one embodiment, please refer to fig. 3, which is a schematic diagram illustrating a structure of an anomaly early warning model according to an embodiment of the present application. The abnormal early warning model comprises a first time sequence model, a second time sequence model, a third time sequence model and a classification model, wherein the first time sequence model is used for extracting time sequence characteristics of the temperature global uniformity sequence to obtain temperature global uniformity characteristics; the second time sequence model is used for extracting time sequence characteristics of the temperature local deviation value sequence to obtain temperature local deviation value characteristics; the third time sequence model is used for extracting time sequence characteristics of the temperature correction fluctuation sequence to obtain temperature correction fluctuation characteristics; and inputting the temperature global uniformity characteristic, the temperature local deviation quantity characteristic and the temperature correction fluctuation characteristic into the classification model to output an abnormality early-warning result at the current moment, wherein the abnormality early-warning result comprises abnormality and normal.
The first time sequence model, the second time sequence model and the third time sequence model are all cyclic neural networks such as LSTM or GRU; the classification model adopts a fully connected network.
It is understood that the early warning is issued in response to the abnormality early warning result being an abnormality. The temperature global uniformity sequence, the temperature local deviation amount sequence and the temperature correction fluctuation sequence can reflect whether the electric heating constant temperature incubator is in an abnormal state or not.
In one embodiment, in order to enable the anomaly early warning model to accurately output the anomaly early warning result, the anomaly early warning model needs to be trained. Specifically, the training method of the anomaly early warning model comprises the following steps: in the history use process of the electric heating constant temperature incubator, acquiring a temperature global uniformity sequence, a temperature local deviation amount sequence and a temperature correction fluctuation sequence of any set time period as input samples, and taking a use state at the last moment of the set time period as a sample label of the input samples, wherein the use state comprises abnormal and normal; inputting the input sample into the abnormal early warning model to obtain an output result; calculating a cross entropy loss function value based on the output result and a sample label of the input sample; performing back propagation according to the cross entropy loss function value, updating the abnormal early warning model, and completing one-time training; and iteratively training the abnormal early warning model until the cross entropy loss function value is smaller than a set loss value, and obtaining the trained abnormal early warning model.
Wherein the value of the set loss value is 0.001.
And inputting the temperature global uniformity sequence, the temperature local deviation amount sequence and the temperature correction fluctuation sequence into the trained abnormal early-warning model to output an abnormal early-warning result at the current moment, and responding to the abnormal early-warning result at the current moment as an abnormality to send out early-warning prompt.
Therefore, real-time early warning is realized in the use process of the electrothermal constant-temperature incubator according to the trained abnormal early warning model, and when the abnormal early warning result output by the abnormal early warning model is abnormal, early warning reminding is timely sent out.
Technical principles and implementation details of the abnormality early warning method of the electrothermal constant temperature incubator of the present application are described above through specific embodiments. According to the technical scheme provided by the application, the temperature fluctuation sequence is obtained according to the change of the average temperature value between adjacent moments in the set time period, and further, the temperature fluctuation sequence is corrected according to the power supply parameter fluctuation sequence in consideration of the influence of power supply parameter fluctuation on the temperature fluctuation, so that the temperature correction fluctuation sequence is obtained, and the temperature correction fluctuation sequence can exclude the temperature change caused by the power supply parameter fluctuation and accurately reflect whether the electric heating constant temperature incubator is in an abnormal state or not; further, a temperature global uniformity sequence and a temperature local deviation amount sequence are acquired, wherein the temperature global uniformity sequence can reflect the temperature global uniformity at each moment in a set time period, and the temperature global uniformity can reflect the deviation between the temperature values at different positions and the target temperature value; the sequence of local temperature deviations can reflect a local temperature deviation amount for each location that can reflect a maximum value of the temperature deviations in the contiguous range of all locations; and finally, inputting the temperature global uniformity sequence, the temperature local deviation sequence and the temperature correction fluctuation sequence into a trained abnormal early warning model to output an abnormal early warning result at the current moment, so that the accuracy of the abnormal early warning is improved while the real-time early warning of the electric heating constant temperature incubator is realized.
According to a second aspect of the application, the application further provides an abnormality early warning system of the electrothermal constant temperature incubator. Fig. 4 is a block diagram of an abnormality early warning system of an electrothermal incubator according to an embodiment of the present application. As shown in fig. 4, the system 50 includes a processor and a memory storing computer program instructions that when executed by the processor implement an anomaly pre-warning method for an electrically heated incubator according to the first aspect of the present application. The system further comprises other components known to those skilled in the art, such as a communication bus and a communication interface, the arrangement and function of which are known in the art and are therefore not described in detail herein.
In the context of this document, the foregoing memory may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, or device. For example, the computer-readable storage medium may be any suitable magnetic or magneto-optical storage medium, such as, for example, resistance change Memory RRAM (Resistive Random Access Memory), dynamic Random Access Memory DRAM (Dynamic Random Access Memory), static Random Access Memory SRAM (Static Random-Access Memory), enhanced dynamic Random Access Memory EDRAM (ENHANCED DYNAMIC Random Access Memory), high-Bandwidth Memory HBM (High-Bandwidth Memory), hybrid storage cube HMC (Hybrid Memory Cube), or the like, or any other medium that may be used to store the desired information and that may be accessed by an application, a module, or both. Any such computer storage media may be part of, or accessible by, or connectable to, the device. Any of the applications or modules described herein may be implemented using computer-readable/executable instructions that may be stored or otherwise maintained by such computer-readable media.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the claims. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (7)
1. An anomaly early warning method of an electrothermal constant temperature incubator is characterized in that a plurality of temperature sensors are arranged in the incubator, the plurality of temperature sensors are distributed in an array, and the anomaly early warning method comprises the following steps:
Acquiring average temperature values of the plurality of temperature sensors at each moment in a set time period, and subtracting the average temperature value of the last adjacent moment from the average temperature value of each moment to obtain a temperature fluctuation sequence, wherein the set time period comprises the current moment and a set number of moments before the current moment;
Subtracting the power supply parameter value of the last adjacent moment from the power supply parameter value of each moment to obtain a power supply parameter fluctuation sequence in the set time period, wherein the power supply parameter values comprise a voltage value and a current value;
constructing a temperature change model, and correcting the temperature fluctuation sequence according to the temperature change model and the power supply parameter fluctuation sequence to obtain a temperature correction fluctuation sequence, wherein the input of the temperature change model is power supply parameter fluctuation, and the output of the temperature change model is temperature change quantity caused by the power supply parameter fluctuation;
Calculating the global uniformity of the temperature at each moment based on the deviation between the temperature values of all the temperature sensors and the target temperature value to construct a global uniformity sequence of the temperature in the set time period;
calculating the temperature gradient of each temperature sensor according to the deviation of the temperature value between one temperature sensor and the adjacent sensor at any time in the set time period, and taking the maximum value of the temperature gradient as the local temperature deviation value at any time to construct a local temperature deviation value sequence in the set time period;
Inputting the temperature global uniformity sequence, the temperature local deviation amount sequence and the temperature correction fluctuation sequence into a trained abnormality early warning model to output an abnormality early warning result at the current moment;
the power supply parameter fluctuation comprises voltage value fluctuation and current value fluctuation, and the construction of the temperature change model comprises the following steps:
Constructing a temperature change initial model, wherein the temperature change initial model meets the relation:
wherein, For current value fluctuation,/>For voltage value fluctuation,/>Is the highest power of current value fluctuation,/>For the fluctuation of the current value/>Current weight corresponding to power,/>For the fluctuation of the current value/>To the power of the two,/(I)Is the highest power of voltage value fluctuation,/>For the fluctuation of voltage value/>Voltage weight corresponding to power,/>For the fluctuation of voltage value/>To the power of the two,/(I)The temperature variation caused by the fluctuation of the power supply parameters is used;
collecting a plurality of groups of training samples, wherein the training samples comprise power supply parameter fluctuation under the normal state of an electrothermal constant temperature incubator and temperature variation corresponding to the power supply parameter fluctuation;
fitting the temperature change initial model on the plurality of groups of training samples by using a least square method, and determining the values of all voltage weights and all current weights so as to obtain a temperature change model;
Correcting the temperature fluctuation sequence according to the temperature change model and the power supply parameter fluctuation sequence, wherein obtaining the temperature correction fluctuation sequence comprises the following steps:
for one moment in the set time period, acquiring power supply parameter fluctuation of the moment based on the power supply parameter fluctuation sequence, inputting the power supply parameter fluctuation into the temperature change model, and taking an output result as a temperature correction quantity of the moment;
acquiring the temperature fluctuation at the moment based on the temperature fluctuation sequence, and subtracting the temperature correction amount at the moment from the temperature fluctuation at the moment to obtain the temperature correction fluctuation at the moment;
and acquiring temperature correction fluctuation at all moments in the set time period, and arranging all the temperature correction fluctuation according to the sequence of the moments to obtain a temperature correction fluctuation sequence.
2. The method for anomaly early warning of an electrically heated incubator according to claim 1, wherein calculating the global uniformity of temperature at each time based on the deviations between the temperature values of all the temperature sensors and the target temperature value to construct the global uniformity sequence of temperature within the set time period comprises:
collecting temperature values of the plurality of temperature sensors for a moment in a set time period;
Calculating the global uniformity of the temperature at the moment based on the deviation between the temperature values of all the temperature sensors and the target temperature value, wherein the global uniformity of the temperature at the moment meets the relation:
wherein, For the number of the plurality of temperature sensors,/>For time/>Time/>Temperature value of individual temperature sensor,/>For the target temperature value,/>For time/>Is a global uniformity of temperature;
and calculating the global uniformity of the temperature at each moment in the set time period, and arranging all the global uniformity of the temperature according to the sequence of the moment to obtain a global uniformity sequence of the temperature.
3. The abnormality early warning method of an electrically heated incubator according to claim 1, characterized in that calculating a temperature gradient of each temperature sensor from a deviation of temperature values between one temperature sensor and adjacent sensors at an arbitrary timing within the set period, and taking a maximum value of the temperature gradient as a temperature local deviation amount at the arbitrary timing includes:
At any time within the set time period, all adjacent sensors of one temperature sensor are obtained, the temperature gradient of the temperature sensor is calculated based on the deviation of the temperature value between the temperature sensor and the adjacent sensors, and the temperature gradient of the temperature sensor meets the relation:
wherein, For contiguous sensor set, includingAll adjacent sensors of the individual temperature sensors,/>For time/>Time/>Temperature value of individual temperature sensor,/>For time/>Time/>The temperature value of each of the adjacent sensors,For/>Number of all adjacent sensors of each temperature sensor,/>For time/>Time/>A temperature gradient of the individual temperature sensors;
and calculating the temperature gradients of all the temperature sensors at any moment, and taking the maximum value of the temperature gradients as the local deviation amount of the temperature at any moment.
4. The abnormality early-warning method of an electrothermal incubator according to claim 1, wherein the abnormality early-warning model includes a first time sequence model, a second time sequence model, a third time sequence model, and a classification model;
the first time sequence model is used for extracting time sequence characteristics of the temperature global uniformity sequence to obtain temperature global uniformity characteristics;
the second time sequence model is used for extracting time sequence characteristics of the temperature local deviation value sequence to obtain temperature local deviation value characteristics;
The third time sequence model is used for extracting time sequence characteristics of the temperature correction fluctuation sequence to obtain temperature correction fluctuation characteristics;
and inputting the temperature global uniformity characteristic, the temperature local deviation quantity characteristic and the temperature correction fluctuation characteristic into the classification model to output an abnormality early-warning result at the current moment, wherein the abnormality early-warning result comprises abnormality and normal.
5. The abnormality early warning method of an electrothermal incubator according to claim 4, characterized in that the training method of the abnormality early warning model includes:
In the history use process of the electric heating constant temperature incubator, acquiring a temperature global uniformity sequence, a temperature local deviation amount sequence and a temperature correction fluctuation sequence of any set time period as input samples, and taking a use state at the last moment of the set time period as a sample label of the input samples, wherein the use state comprises abnormal and normal;
inputting the input sample into the abnormal early warning model to obtain an output result;
calculating a cross entropy loss function value based on the output result and a sample label of the input sample;
performing back propagation according to the cross entropy loss function value, updating the abnormal early warning model, and completing one-time training;
and iteratively training the abnormal early warning model until the cross entropy loss function value is smaller than a set loss value, and obtaining the trained abnormal early warning model.
6. The abnormality early warning method of an electrically heated incubator according to claim 4, characterized in that the early warning reminder is issued in response to the abnormality early warning result at the present moment being abnormal.
7. An anomaly early warning system of an electrothermal incubator, characterized by comprising a processor and a memory, the memory storing computer program instructions which, when executed by the processor, implement an anomaly early warning method of an electrothermal incubator according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410194421.6A CN117786464B (en) | 2024-02-22 | 2024-02-22 | Abnormality early warning method and system for electric heating constant temperature incubator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410194421.6A CN117786464B (en) | 2024-02-22 | 2024-02-22 | Abnormality early warning method and system for electric heating constant temperature incubator |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117786464A CN117786464A (en) | 2024-03-29 |
| CN117786464B true CN117786464B (en) | 2024-05-24 |
Family
ID=90392789
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410194421.6A Active CN117786464B (en) | 2024-02-22 | 2024-02-22 | Abnormality early warning method and system for electric heating constant temperature incubator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117786464B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021204010A1 (en) * | 2020-11-19 | 2021-10-14 | 平安科技（深圳）有限公司 | Time series anomaly detection method and apparatus, and computer device and storage medium |
| CN115840897A (en) * | 2023-02-09 | 2023-03-24 | 广东吉器电子有限公司 | Temperature sensor data exception handling method |
| CN116414097A (en) * | 2023-05-15 | 2023-07-11 | 广东思创智联科技股份有限公司 | Alarm management method and system based on industrial equipment data |
| CN116432542A (en) * | 2023-06-12 | 2023-07-14 | 国网江西省电力有限公司电力科学研究院 | Switch cabinet busbar temperature rise early warning method and system based on error sequence correction |
| CN117258932A (en) * | 2023-09-27 | 2023-12-22 | 浙江艾领创矿业科技有限公司 | Temperature monitoring system and method of intelligent sand mill |
| CN117375237A (en) * | 2023-10-20 | 2024-01-09 | 浙江日新电气有限公司 | Substation operation and maintenance method and system based on digital twin technology |
-
2024
- 2024-02-22 CN CN202410194421.6A patent/CN117786464B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021204010A1 (en) * | 2020-11-19 | 2021-10-14 | 平安科技（深圳）有限公司 | Time series anomaly detection method and apparatus, and computer device and storage medium |
| CN115840897A (en) * | 2023-02-09 | 2023-03-24 | 广东吉器电子有限公司 | Temperature sensor data exception handling method |
| CN116414097A (en) * | 2023-05-15 | 2023-07-11 | 广东思创智联科技股份有限公司 | Alarm management method and system based on industrial equipment data |
| CN116432542A (en) * | 2023-06-12 | 2023-07-14 | 国网江西省电力有限公司电力科学研究院 | Switch cabinet busbar temperature rise early warning method and system based on error sequence correction |
| CN117258932A (en) * | 2023-09-27 | 2023-12-22 | 浙江艾领创矿业科技有限公司 | Temperature monitoring system and method of intelligent sand mill |
| CN117375237A (en) * | 2023-10-20 | 2024-01-09 | 浙江日新电气有限公司 | Substation operation and maintenance method and system based on digital twin technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117786464A (en) | 2024-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gao et al. | Integrated equivalent circuit and thermal model for simulation of temperature-dependent LiFePO4 battery in actual embedded application | |
| Xiong et al. | A double-scale, particle-filtering, energy state prediction algorithm for lithium-ion batteries | |
| Zeng et al. | An online state of charge estimation algorithm for lithium-ion batteries using an improved adaptive cubature Kalman filter | |
| Sun et al. | Online internal temperature estimation for lithium-ion batteries based on Kalman filter | |
| Yang et al. | State of charge estimation for lithium-ion battery with a temperature-compensated model | |
| CN102722197B (en) | Self-calibration temperature control device and method | |
| Zhang et al. | Estimation of state of charge of lithium-ion batteries used in HEV using robust extended Kalman filtering | |
| Lv et al. | The influence of temperature on the capacity of lithium ion batteries with different anodes | |
| Beucler et al. | Climate-invariant machine learning | |
| CN115147012B (en) | Neural network model-based carbon emission accounting method and device | |
| Jin et al. | Comparison of SOC estimation between the integer-order model and fractional-order model under different operating conditions | |
| JPWO2020137914A5 (en) | ||
| CN117786464B (en) | Abnormality early warning method and system for electric heating constant temperature incubator | |
| Dubarry et al. | Battery durability and reliability under electric utility grid operations: analysis of on-site reference tests | |
| CN109814037A (en) | Acquisition methods, terminal device and the medium of the hot coefficient of lithium ion battery entropy | |
| Xu et al. | A hybrid observer for SOC estimation of lithium-ion battery based on a coupled electrochemical-thermal model | |
| Xing et al. | Lithium-ion battery state-of-charge estimation based on a dual extended Kalman filter and BPNN correction | |
| CN110598336B (en) | Water consumption prediction method and device for water heater, water heater and electronic equipment | |
| Jiang et al. | Online state-of-charge estimation based on the gas–liquid dynamics model for Li (NiMnCo) O2 battery | |
| Mao et al. | An electrical–thermal coupling model with artificial intelligence for state of charge and residual available energy Co-estimation of LiFePO4 battery system under various temperatures | |
| US8700546B2 (en) | Model based calibration of inferential sensing | |
| Degla et al. | Comparison study and parameter identification of three battery models for an off-grid photovoltaic system | |
| Wang et al. | A novel ultracapacitor state-of-charge fusion estimation method for electric vehicles considering temperature uncertainty | |
| CN113699032A (en) | Incubator and control method and device | |
| Zeng et al. | The evaluation of battery pack SOH based on Monte Carlo simulation and support vector machine algorithm |
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 |