CN116449081A - Data acquisition system, device and storage medium with self-adaptive regulation and control function - Google Patents
Data acquisition system, device and storage medium with self-adaptive regulation and control function Download PDFInfo
- Publication number
- CN116449081A CN116449081A CN202310706225.8A CN202310706225A CN116449081A CN 116449081 A CN116449081 A CN 116449081A CN 202310706225 A CN202310706225 A CN 202310706225A CN 116449081 A CN116449081 A CN 116449081A
- Authority
- CN
- China
- Prior art keywords
- data
- real
- time current
- current data
- hidden state
- 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.)
- Granted
Links
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 238000012544 monitoring process Methods 0.000 claims abstract description 77
- 238000005457 optimization Methods 0.000 claims abstract description 74
- 238000005070 sampling Methods 0.000 claims abstract description 66
- 230000007704 transition Effects 0.000 claims abstract description 50
- 238000000034 method Methods 0.000 claims abstract description 42
- 230000008859 change Effects 0.000 claims description 96
- 230000006870 function Effects 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 25
- 238000004364 calculation method Methods 0.000 claims description 21
- 230000003044 adaptive effect Effects 0.000 claims description 18
- 230000008569 process Effects 0.000 abstract description 25
- 238000010586 diagram Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 7
- 238000012937 correction Methods 0.000 description 6
- 238000009826 distribution Methods 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000008030 elimination Effects 0.000 description 5
- 238000003379 elimination reaction Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000011056 performance test Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/0092—Arrangements for measuring currents or voltages or for indicating presence or sign thereof measuring current only
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of computers, in particular to a data acquisition system with a self-adaptive regulation function, a device and a storage medium, comprising the following components: acquiring real-time current data output by a charging pile; the method comprises the steps of obtaining state transition probability differences through a hidden Markov model, optimizing real-time current data, and obtaining initial data; calculating a noise optimization factor in a hidden state of real-time current data at a preset position in the initial data; optimizing the real-time current data according to the noise optimization factor to obtain optimized real-time current data, and calculating the current variation according to the optimized real-time current data; and adjusting the sampling frequency of the current data according to the current variation, and adjusting the sampling frequency according to the judgment result, so that the problem of random electronic noise in the process of monitoring the output current of the charging pile can be solved, and the data accuracy of the data intelligent acquisition system is ensured.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a data acquisition system, apparatus, and storage medium with a self-adaptive regulation function.
Background
The test system of the charging pile of the new energy automobile is mainly used for verifying and confirming the functions and performances of the charging pile so as to ensure the safety and effectiveness of the charging pile in actual operation. In the charging pile test system, parameters such as voltage, current, power, electric energy and the like of the charging pile are required to be tested through an electric performance test device. And (5) carrying out real-time monitoring through the collected data, and verifying the performance and the function of the charging pile. The self-adaptive sampling frequency regulation and control are carried out in the current testing equipment, and the sampling frequency can be dynamically regulated according to the degree of current change, so that the complexity and cost of data processing are reduced while the testing precision is ensured.
In the existing regulation and control process, a current change threshold value is defined first, the sampling frequency is increased when the monitored change of the current exceeds the threshold value, and the sampling frequency is reduced when the current change is smaller than the threshold value. And then, calculating the change of the current according to the real-time monitoring data, and adjusting the dynamic sampling frequency according to the judgment result.
However, in the existing process of adaptively adjusting the sampling frequency of the current monitoring data of the charging pile, because random electronic noise generated by the electronic equipment during the working process exists in the monitoring of the output current of the charging pile in an actual scene, the noise is determined by physical characteristics of the electronic equipment, such as resistance, semiconductor materials and the like, and the noise can cause deviation in calculation of the variation of the current monitoring value, such as that for a monitored output current value at a certain moment, the value is larger due to the noise, so that the current variation exceeds the current variation threshold value, and thus the sampling frequency is erroneously adjusted.
Disclosure of Invention
In view of the foregoing, embodiments of the present invention are provided to provide a data acquisition system, apparatus and storage medium with adaptive regulation and control function, which overcomes or at least partially solves the foregoing problems.
In order to achieve the above objective, an embodiment of the present invention provides a data acquisition system, a device and a storage medium with an adaptive regulation function, where implementation steps of the system include:
acquiring real-time current data output by a charging pile;
the method comprises the steps of obtaining state transition probability differences through a hidden Markov model, optimizing real-time current data, and obtaining initial data;
calculating a noise optimization factor in a hidden state of real-time current data at a preset position in the initial data;
optimizing the real-time current data according to the noise optimization factor to obtain optimized real-time current data, and calculating the current variation according to the optimized real-time current data;
and adjusting the sampling frequency of the current data according to the current variation.
Preferably, the optimizing the real-time current data by obtaining the state transition probability difference through the hidden markov model, obtaining initial data includes:
Calculating a next predicted current monitoring value and a predicted hiding state of the real-time current data, and a next actual monitoring value and a corresponding hiding state;
obtaining the difference between the predicted hidden state transition probability and the actual hidden state transition probability of the next data point according to the next predicted current monitoring value and the predicted hidden state, and the next actual monitoring value and the corresponding hidden state;
determining the difference between the predicted hidden state transition probability and the actual hidden state transition probability of the next data point as a real-time current data optimization quantity to obtain first initial data;
repeating the steps to obtain the initial data with preset quantity.
Preferably, the calculating the noise optimization factor in the hidden state of the real-time current data at the preset position in the initial data includes:
calculating trend change factors in hidden states of the preset quantity of initial data;
and calculating a noise optimization factor of the initial data according to the trend change factor.
Preferably, the calculating the trend change factor in the hidden state of the preset amount of initial data includes:
calculating the number of data points with consistent directions, the length of a window, the number of continuous changes of the variation, a data point set with consistent directions and a data point difference value;
And obtaining a trend change factor in the hidden state according to the number of data points with consistent directions, the window length, the number of continuous changes of the change quantity, the data point set with consistent directions and the data point difference value.
Preferably, the noise optimization factor calculated according to the trend change factor to obtain the initial data includes:
acquiring a trend change factor, a numerical difference distance of a hidden state boundary, a first probability and a second probability;
and calculating to obtain a noise optimization factor of the initial data according to the trend change factor, the numerical difference distance of the hidden state boundary, the first probability and the second probability.
Preferably, the optimizing the real-time current data according to the noise optimizing factor to obtain optimized real-time current data, and calculating the current variation according to the optimized real-time current data includes:
when the hidden state is unchanged, obtaining optimized real-time current data according to the noise optimization factor, the actual monitoring value and the state change judgment factor;
and determining the difference value of the optimized real-time current data and the previous real-time current data as the current variation.
Preferably, the adjusting the sampling frequency of the current data according to the current variation includes:
When the current variation is larger than the threshold value of the quick charging pile, adjusting the sampling frequency to a first sampling frequency;
and when the current variation is smaller than or equal to the threshold value of the quick charging pile, adjusting the sampling frequency to a second sampling frequency.
The embodiment of the invention provides a data acquisition device with a self-adaptive regulation function, which comprises:
the real-time current data acquisition module is used for acquiring real-time current data output by the charging pile;
the initial data acquisition module is used for optimizing the real-time current data by acquiring the state transition probability difference through the hidden Markov model to acquire initial data;
the noise optimization factor calculation module is used for calculating a noise optimization factor in a hidden state of real-time current data at a preset position in the initial data;
the current variation calculation module is used for optimizing the real-time current data according to the noise optimization factor to obtain optimized real-time current data, and calculating the current variation according to the optimized real-time current data;
and the sampling frequency adjusting module is used for adjusting the sampling frequency of the current data according to the current variation.
The embodiment of the invention discloses a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, realizes the steps of the data acquisition system with the self-adaptive regulation and control function.
In the embodiment of the invention, in the process that the hidden Markov model of the real-time monitoring data acquires the hidden state prediction sequence through the Viterbi algorithm, the noise correction in the same state range corresponding to the hidden state prediction result of the next data point is carried out through the real-time local distribution condition of the latest data point, compared with the noise judgment and adjustment carried out through the hidden state prediction result of the hidden Markov model alone, the adjustment of the data point in the normal state according to the distribution condition of the local data point can be ensured, and the predicted value of the data point is optimized under the condition that the noise does not cause the state change of the data point, thereby eliminating the noise of the real-time monitoring data to the maximum extent and ensuring the accurate predicted result of the subsequent data point. When the data point value is optimized through the prediction result, the current change calculated by the optimized current monitoring value is ensured to accurately adjust the self-adaptive sampling frequency, so that the intelligent acquisition effect of reducing the complexity and cost of data processing is achieved; predicting the hidden state of the next current monitoring data point through real-time monitoring data, measuring the difference through the difference between the hidden state of the actual data point and the predicted hidden state after the next current monitoring data point is acquired, eliminating the noise of the data point according to the difference between the hidden state of the actual data point and the predicted hidden state, and judging the threshold value of the current change through the output current monitoring value of the charging pile after the noise elimination, thereby being used as the basis for self-adaptive sampling frequency adjustment; compared with the method that the current change threshold value is judged by directly monitoring the output current monitoring value of the charging pile in real time, and the sampling frequency is adjusted according to the judging result, the problem of random electronic noise in the process of monitoring the output current of the charging pile can be eliminated, and the data accuracy of a data acquisition system is ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of steps of an embodiment of a data acquisition system with adaptive regulation and control functionality according to an embodiment of the present invention;
FIG. 2 is a flow chart of an initial data acquisition step according to an embodiment of the present invention;
fig. 3 is a schematic diagram of output current of a charging pile according to an embodiment of the present invention;
FIG. 4 is a flowchart of a noise optimization factor acquisition step of an embodiment of the present invention;
FIG. 5 is a flowchart of a trend change factor acquisition step according to an embodiment of the present invention;
FIG. 6 is a flowchart of a noise optimization factor acquisition step of an embodiment of the present invention;
FIG. 7 is a flow chart of a current variation calculation step of an embodiment of the present invention;
fig. 8 is a block diagram of an embodiment of a data acquisition device with adaptive regulation and control function according to an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical schemes and beneficial effects solved by the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, a flowchart illustrating steps of an embodiment of a data acquisition system with adaptive regulation and control function according to an embodiment of the present invention may specifically include the following steps:
step 101, acquiring real-time current data output by a charging pile;
for the execution body of the embodiment of the invention, the system can be applied to a terminal, and the terminal can be a tablet personal computer, a personal computer, an integrated computer and the like.
Firstly, the real-time current data output by the charging pile can be acquired through the direct current detection device, and a hidden Markov model for predicting the state of the data points can be preset.
Step 102, optimizing real-time current data by acquiring state transition probability differences through a hidden Markov model, and acquiring initial data;
in the embodiment of the invention, when the electric performance test is carried out on the charging piles, the electric performance detection results of the charging piles of the same model are the same, but random electronic noise exists in the charging piles, so that the noise judgment of data points can be carried out on the output current monitoring data of the charging piles of the same model collected in a historical manner, and a hidden Markov model is constructed through the historical monitoring data. In the hidden markov model, data points are divided into a high noise cluster class, a low noise cluster class and eight normal data point cluster classes through K=10 clusters.
In the core concept of the embodiment of the invention, after the hidden Markov model for judging the noise of the subsequent data points is obtained, the hidden state of the data points can be predicted in the process of collecting the real-time current data of the charging pile through the current monitor, and the random electronic noise influence in the real-time monitoring data points is eliminated by combining the actual monitoring result with the prediction result. And judging the threshold value of sampling frequency adjustment according to the optimized current change.
The method is particularly applied to the embodiment of the invention, and after the hidden Markov model for predicting the hidden state of the charging pile at the next moment and the real-time charging pile output current data are obtained, the data are acquired. And carrying out change measurement on the current data point due to random electronic noise on each data point through the local actual monitoring current data fluctuation condition and the optimized hidden state change condition of the data point, acquiring the noise degree in the data point, and optimizing the actual monitoring value of the next data point according to the noise degree, so that the size of the influence of noise on the data point can be measured under the condition that the hidden state change of the data point does not occur, and the hidden Markov model is accurate for the hidden state prediction of the subsequent data point.
In the embodiment of the present invention, referring to fig. 2, a flowchart of an initial data acquisition step according to the embodiment of the present invention is shown, including the following sub-steps:
step 11, calculating a next predicted current monitoring value and a predicted hiding state of the real-time current data, and a next actual monitoring value and a corresponding hiding state;
Step 12, obtaining the difference between the predicted hidden state transition probability and the actual hidden state transition probability of the next data point according to the next predicted current monitoring value and the predicted hidden state;
step 13, determining the difference between the predicted hidden state transition probability and the actual hidden state transition probability of the next data point as a real-time current data optimization quantity, and obtaining first initial data;
and a sub-step 14, repeating the steps to obtain the initial data with preset quantity.
In the embodiment of the invention, the size of a local window is required to be set in the process of carrying out the local change analysis of the data points, so that the analysis range of each real-time monitoring data point is determined. In the present invention, if the local window length l=10 is set, then the numerical optimization of the first 10 data points needs to be performed by using the hidden markov model alone, and of course, other local window lengths may also be set, for example, the local window length l=20 or 30, which is not limited too much in the embodiment of the present invention.
In the monitoring of the output current of a charging pile, an accurate first current monitoring value is obtained for a first data point through multiple sampling, and the hidden state can be predicted through a Viterbi algorithm according to a hidden Markov model from the first current monitoring value to obtain a subsequent hidden state sequence. At this time for the value of the first data point Can obtain +.>Predicted hidden state->Next, data point +.>Acquiring the actual value of (1) to obtain the actual monitoring value +.>Hidden state corresponding to the actual monitoring value +.>Through the combination of->And judging whether the hidden state changes or not. If a change occurs, by->The corresponding state probability transition matrix is used for judging, and the corresponding state change is +>Acquiring corresponding state transition probability->. Whereas for predicted state transition probability +.>Actual data point +.>For->Data point optimization numerical value corresponding to moment：
Equation 1;
wherein the symbols of formula 1 have the following meanings;
: representation->Time of day is +.>The optimized data value, i.e. the initial data.
: represents a state change judgment factor for +.>And judging the data point at the moment according to the difference between the actual state and the predicted state of the actually collected data point. When->At->In the upper part, the factor is +.>Otherwise, 1.
: represented in a hidden Markov model, +.>In the state probability transition matrix of the data points at the moment in time,is a probability of (2).
: represented in a hidden Markov model, +. >In the state probability transition matrix of the data points at the moment in time,is a probability of (2).
: representation->The current of the charging pile at the moment is actually acquired.
For the first in real-time monitoring dataHidden state corresponding to data point at each moment +.>The most probable hidden state sequence can be obtained by means of the viterbi algorithm based on the hidden markov model, relative to +.>Is->I.e. the corresponding predictive hidden state can be obtained>. After that pair->Is acquired by collecting the actual data of (1)>For this actual data the true hidden state +.>. For->I.e. pass->And->The difference between them corrects it.
For accurate data points after noise elimination, the prediction result of the hidden Markov model is the prediction of the numerical value at the next moment according to the historical data. By means of a state probability transition matrix during prediction, it is possible to do so by means of the difference between the predicted hidden state transition probability and the actual hidden state transition probability of the next data pointIs used for the correction of (a). For numerical division in current time series data, data points with noise influence are located at the uppermost and lowermost of time series data, so that the data points are required to pass +. >Go->And judging the correction direction. To->As a measure of the correction size, the transition probability difference of the two states is taken as +.>The optimization amount of (2) aims at regarding the amount causing abnormal state transition as noise and removing the noise in value to achieve the effect of optimization.
According to the above calculation steps, a preset number of initial data are obtained, for example, the first 10 optimized data points of the output current data of the charging pile can be determined and used as the firstData points within a local window of data points.
Step 103, calculating a noise optimization factor in a hidden state of real-time current data at a preset position in the initial data;
in the method for eliminating sampling noise in the process of carrying out real-time monitoring on output current of charging pile through hidden Markov prediction model, only prediction is carried outThe random electronic noise optimization of the data points can be performed only when the difference exists between the hidden state of the data points at the moment and the actual hidden state. However, in the actual scenario, there is still a state that is the same as the actual hidden state for the next data point, and then it is considered noise-free in the existing optimization process.
There will be situations where the noise impact is small, but there is also noise in the collected data points, except that the noise does not change the hidden state of the data points. But rather the effect of having the data point in the same hidden state interval. Then for the optimization process described aboveIn practice, more careful alignment is requiredThe data points at the moment are subjected to local window analysis to eliminate noise influence on the data points.
After the first ten data of the output current of the whole charging pile are obtained in the optimization process, noise measurement of the data points can be started through data point changes in the local window.
For example, as shown in fig. 3, for the first ten data points of the output current of the charging pile, the box represents the hidden state range:
in the window, the data points are all in the same hidden state, so that the optimization calculation of the current variation is not performed in the process. In this case, for the t-th data point (t>10 The set Ω (t) pair can be determined by 10L data points preceding the t-th data point as windowsAnd the noise level of the (c) is judged. Since the sampling frequency is as low as 10 Hz for 10 data points, i.e. 1 second, during the monitoring of the output current of the charging pile. The data points within the window should be stationary. Then for- >The less stationary the data point in its window Ω (t) changes, the higher the noise contained in the data point. And for the fluctuation of the data point in the same hidden state interval, when the hidden state transition trend of the data point exists, the higher the hidden state change trend of the data point is, the more noise elimination similar to the hidden state change is carried out according to the fluctuation degree of the data point in the window.
Specifically, referring to fig. 4, a flowchart of a noise optimization factor acquisition step according to an embodiment of the present invention is shown, including the following sub-steps:
step 21, calculating trend change factors in hidden states of the preset quantity of initial data;
referring to fig. 5, which shows a flowchart of a trend change factor obtaining step according to an embodiment of the present invention, sub-step 21 includes the sub-steps of:
step 211, calculating the number of data points with consistent directions, the length of a window, the number of continuous changes of the variation, the data point set with consistent directions and the data point difference value;
in step 212, a trend change factor in the hidden state is obtained according to the number of data points with consistent directions, the window length, the number of continuous changes in the change amount, the data point set with consistent directions and the data point difference value.
For example, for the firstTrend change factor of data point in hidden state +.>：
Equation 2;
wherein the symbol of formula 2 has the following meaning;
: is indicated at->In the window, for each data point, the direction of change from the previous data point to that data point is equal to +.>Is a number of data points that are consistent in direction.
: represents the window length set, in this embodiment +.>Set to->。
: the representation is compared with +.>Has a continuously variable number of values, i.e. in +.>The number of consecutive changes in data points in the change in the previous data point.
: is indicated at->In the window, for each data point, the direction of change from the previous data point to that data point is equal to +.>Is a set of data points that are consistent in direction.
: is indicated at->The%>Data points minus +.>Middle->Data points are +.>The previous data point of (c).
At the position ofWindow of->In (1), need to be right->The judgment of the fluctuation trend information is made with the aim of judging when +.>Compared with +.>If the variation trend of (2) is in conformity with->If the overall trend of (c) changes, then the data point changes within the window are stable, then the noise impact is less because random noise cannot stably change the data point affected by it. In the measurement process, first judging +. >Whether the direction of (a) corresponds to the trend direction of the window as a whole, here by the number ratio of data points +.>Make a judgment, then for +.>By the continuously varying amount of the trend variable +.>It is decided that if the number of continuous changes is greater, the "acceleration" indicating the change in the value is higher, then for +.>Predictive value optimization of (a)The degree of optimization can be measured according to whether it is close to the hidden state boundary. Finally, all and ++in the window are judged according to the degree of quantity>Mean calculation of data points with the same trend direction +.>It is taken as +.>Is optimized and judged. Finally pass->And (5) carrying out normalization processing. A trend change factor is obtained. In this process, the more uniform the trend, the description is for +.>The smaller the noise effect, the lower the noise effect can be>Is adjusted.
After the trend change factor is obtained, the trend change factor can be obtained byThe distance between the value of (2) and the boundary of the hidden state is determined when +.>The smaller the distance of the value of (2) from the boundary of the hidden state, the description +.>The more the hidden state tends to change, the more the noise optimization factor needs to be judged according to the distance. And is optimized by a trend change factor on the basis.
And a sub-step 22 of calculating a noise optimization factor of the initial data according to the trend change factor.
Referring to fig. 6, which shows a flowchart of a noise optimization factor acquisition step of an embodiment of the present invention, sub-step 22 includes the sub-steps of:
a substep 221, obtaining a trend change factor, a numerical difference distance of a hidden state boundary, a first probability and a second probability;
in step 222, a noise optimization factor of the initial data is calculated according to the trend change factor, the numerical difference distance of the hidden state boundary, the first probability and the second probability.
For example, for the firstNoise optimization factor of each real-time monitoring data point +.>：
Equation 3;
wherein the symbols of formula 3 have the following meanings;
: indicate->Data points>Trend change factor of the actual monitored value of (c).
: is indicated at->When no change of hidden state occurs during (a) process, is>And->The numerical difference distance of the hidden state boundary in the trend change direction.
: represented in a hidden Markov model, +.>In the state probability transition matrix of the data points at the moment in time,i.e. the first probability.
: represented in a hidden Markov model, +.>In the state probability transition matrix of the data points at the moment in time, I.e. the second probability.
In the first placeData points>And->When there is no hidden state change, the user needs to pass +.>Is a local window of (2)Trend change information and->Distance to trend direction boundaryThe difference between the transition probabilities of hidden state transitions in the direction makes the acquisition of the noise optimization factor.
Noise correction in the same state range corresponding to the hidden state prediction result of the next data point is carried out through the real-time local distribution condition of the latest data point in the process of acquiring the hidden state prediction sequence through the Viterbi algorithm based on the hidden Markov model of the real-time monitoring data, compared with noise judgment and adjustment carried out through the hidden state prediction result of the hidden Markov model alone, the adjustment of the data point in a normal state according to the distribution condition of the local data point can be ensured, and the predicted value of the data point is optimized under the condition that the noise does not cause the state change of the data point, so that the noise of the real-time monitoring data is eliminated to the greatest extent, and the accuracy of the predicted result of the subsequent data point is ensured. Therefore, when the data point value is optimized through the prediction result, the current change calculated by the optimized current monitoring value can be accurately adjusted in the self-adaptive sampling frequency, and the intelligent acquisition effect of reducing the complexity and cost of data processing is achieved.
Step 104, optimizing the real-time current data according to the noise optimization factor to obtain optimized real-time current data, and calculating the current variation according to the optimized real-time current data;
referring to fig. 7, a flow chart of a current variation calculation step of an embodiment of the present invention is shown, the sub-steps comprising:
step 31, when the hidden state is not changed, obtaining optimized real-time current data according to the noise optimization factor, the actual monitoring value and the state change judgment factor;
and a sub-step 32 of determining the difference value between the optimized real-time current data and the previous real-time current data as the current variation.
In the embodiment of the invention, the noise influence in the data points acquired in real time is eliminated by selecting a noise optimization mode through judging the hidden state change of the data points, and the current change value is calculated according to the data points after noise elimination.
Specifically, after the noise optimization factor of the data point is obtained, an interpretation optimization mode can be performed through whether the hidden state changes or not in the process of real-time monitoring.
For the case of the hidden state change, the transition probability difference between the hidden Markov prediction result and the hidden state of the actual result can be optimized, namely 。
For the case that the hidden state is not changed, the noise optimization factor is based on the aboveOptimization of the data point data values is performed. For actual monitoring values +.>：
Equation 4;
after the optimized real-time monitoring value is obtained. For the current variation：
Equation 5;
it should be noted that it is determined for each known data point to be an optimized value. I.e. in the calculation ofAfter that, it is regarded as->Recording is performed and the value is recorded as the current moment +.>And doing soThe optimization process for the next data point.
And step 105, adjusting the sampling frequency of the current data according to the current variation.
In the embodiment of the present invention, the adjusting the sampling frequency of the current data according to the current variation includes the following two cases: when the current variation is larger than the threshold value of the quick charging pile, adjusting the sampling frequency to a first sampling frequency; and when the current variation is smaller than or equal to the threshold value of the quick charging pile, adjusting the sampling frequency to a second sampling frequency.
In a specific example of the embodiment of the present invention, after the current variation amount at each time is obtained by eliminating the current data after random electronic noise, the threshold value can be adjusted according to the sampling frequency Judgment is carried out, and the threshold value is +.>Setting +.>(the threshold is based on +.f. of rated current of output current of charging pile)>Make a determination), when->At this time, the sampling frequency is adjusted to +.>When->At this time, the sampling frequency is adjusted to +.>. The high-frequency acquisition in the sampling frequency of the output current in the electric performance test of the charging pile is the acquisition of +/s>Data, i.e.)>The method comprises the steps of carrying out a first treatment on the surface of the The low frequency acquisition is +/s per second>Data, i.e.)>。
In the embodiment of the invention, in the process that the hidden Markov model of the real-time monitoring data acquires the hidden state prediction sequence through the Viterbi algorithm, the noise correction in the same state range corresponding to the hidden state prediction result of the next data point is carried out through the real-time local distribution condition of the latest data point, compared with the noise judgment and adjustment carried out through the hidden state prediction result of the hidden Markov model alone, the adjustment of the data point in the normal state according to the distribution condition of the local data point can be ensured, and the predicted value of the data point is optimized under the condition that the noise does not cause the state change of the data point, thereby eliminating the noise of the real-time monitoring data to the maximum extent and ensuring the accurate predicted result of the subsequent data point. When the data point value is optimized through the prediction result, the current change calculated by the optimized current monitoring value is ensured to accurately adjust the self-adaptive sampling frequency, so that the intelligent acquisition effect of reducing the complexity and cost of data processing is achieved; predicting the hidden state of the next current monitoring data point through real-time monitoring data, measuring the difference through the difference between the hidden state of the actual data point and the predicted hidden state after the next current monitoring data point is acquired, eliminating the noise of the data point according to the difference between the hidden state of the actual data point and the predicted hidden state, and judging the threshold value of the current change through the output current monitoring value of the charging pile after the noise elimination, thereby being used as the basis for self-adaptive sampling frequency adjustment; compared with the method that the current change threshold value is judged by directly monitoring the output current monitoring value of the charging pile in real time, and the sampling frequency is adjusted according to the judging result, the problem of random electronic noise in the process of monitoring the output current of the charging pile can be eliminated, and the data accuracy of a data acquisition system is ensured.
It should be noted that, for simplicity of description, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the embodiments are not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred embodiments, and that the acts are not necessarily required by the embodiments of the invention.
Referring to fig. 8, a block diagram of an embodiment of a data acquisition device with adaptive regulation and control function according to an embodiment of the present invention is shown, which may specifically include the following modules:
the real-time current data acquisition module 301 is configured to acquire real-time current data output by the charging pile;
the initial data acquisition module 302 is configured to acquire a state transition probability difference through a hidden markov model, optimize real-time current data, and acquire initial data;
the noise optimization factor calculation module 303 is configured to calculate a noise optimization factor in a hidden state of real-time current data at a preset position in the initial data;
The current variation calculation module 304 is configured to optimize the real-time current data according to the noise optimization factor, obtain optimized real-time current data, and calculate a current variation according to the optimized real-time current data;
and the sampling frequency adjustment module 305 is configured to adjust the sampling frequency of the current data according to the current variation.
Preferably, the initial data acquisition module includes:
the state calculation sub-module is used for calculating a next predicted current monitoring value and a predicted hiding state of the real-time current data, and a next actual monitoring value and a corresponding hiding state;
the difference acquisition sub-module is used for obtaining the difference between the predicted hidden state transition probability and the actual hidden state transition probability of the next data point according to the next predicted current monitoring value and the predicted hidden state, and the next actual monitoring value and the corresponding hidden state;
the initial data acquisition sub-module is used for determining the difference between the predicted hidden state transition probability and the actual hidden state transition probability of the next data point as the real-time current data optimization quantity to obtain first initial data;
and the repeating sub-module is used for repeating the steps to obtain the initial data with preset quantity.
Preferably, the noise optimization factor calculation module includes:
the trend change factor calculation sub-module is used for calculating trend change factors in hidden states of the preset quantity of initial data;
and the noise optimization factor calculation sub-module is used for calculating the noise optimization factor of the initial data according to the trend change factor.
Preferably, the trending change factor calculation submodule includes:
the first calculation unit is used for calculating the number of data points with consistent directions, the length of a window, the number of continuous changes of the variation, the data point set with consistent directions and the data point difference value;
the trend change factor obtaining unit is used for obtaining the trend change factor in the hidden state according to the number of data points with consistent directions, the window length, the number of continuous changes of the change quantity, the data point set with consistent directions and the data point difference value.
Preferably, the noise optimization factor calculation submodule includes:
the first acquisition unit is used for acquiring a trend change factor, a numerical difference distance of a hidden state boundary, a first probability and a second probability;
the noise optimization factor obtaining unit is used for calculating the noise optimization factor of the initial data according to the trend change factor, the numerical difference distance of the hidden state boundary, the first probability and the second probability.
Preferably, the current variation amount calculation module includes:
the optimized real-time current data obtaining sub-module is used for obtaining the optimized real-time current data according to the noise optimizing factor, the actual monitoring value and the state change judging factor when the hidden state is not changed;
and the determining submodule is used for determining the difference value between the optimized real-time current data and the previous real-time current data as the current variation.
Preferably, the sampling frequency adjustment module includes:
the first sampling frequency adjustment sub-module is used for adjusting the sampling frequency to the first sampling frequency when the current variation is larger than the threshold value of the quick charging pile;
and the second sampling frequency adjustment sub-module is used for adjusting the sampling frequency to the second sampling frequency when the current variation is smaller than or equal to the threshold value of the quick charging pile.
The modules in the adaptive sampling device for charging pile current can be implemented in whole or in part by software, hardware and combinations thereof.
The self-adaptive sampling device for the current of the charging pile can be used for executing the data acquisition system with the self-adaptive regulation and control function provided by any embodiment, and has corresponding functions and beneficial effects.
In a preferred embodiment, the processor, when executing the computer program, performs the steps of:
calculating a next predicted current monitoring value and a predicted hiding state of the real-time current data, and a next actual monitoring value and a corresponding hiding state;
obtaining the difference between the predicted hidden state transition probability and the actual hidden state transition probability of the next data point according to the next predicted current monitoring value and the predicted hidden state, and the next actual monitoring value and the corresponding hidden state;
determining the difference between the predicted hidden state transition probability and the actual hidden state transition probability of the next data point as a real-time current data optimization quantity to obtain first initial data;
repeating the steps to obtain the initial data with preset quantity.
In a preferred embodiment, the processor, when executing the computer program, performs the steps of:
calculating trend change factors in hidden states of the preset quantity of initial data;
and calculating a noise optimization factor of the initial data according to the trend change factor.
In a preferred embodiment, the processor, when executing the computer program, performs the steps of:
calculating the number of data points with consistent directions, the length of a window, the number of continuous changes of the variation, a data point set with consistent directions and a data point difference value;
And obtaining a trend change factor in the hidden state according to the number of data points with consistent directions, the window length, the number of continuous changes of the change quantity, the data point set with consistent directions and the data point difference value.
In a preferred embodiment, the processor, when executing the computer program, performs the steps of:
acquiring a trend change factor, a numerical difference distance of a hidden state boundary, a first probability and a second probability;
and calculating to obtain a noise optimization factor of the initial data according to the trend change factor, the numerical difference distance of the hidden state boundary, the first probability and the second probability.
In a preferred embodiment, the processor, when executing the computer program, performs the steps of:
when the hidden state is unchanged, obtaining optimized real-time current data according to the noise optimization factor, the actual monitoring value and the state change judgment factor;
and determining the difference value of the optimized real-time current data and the previous real-time current data as the current variation.
In a preferred embodiment, the processor, when executing the computer program, performs the steps of:
when the current variation is larger than the threshold value of the quick charging pile, adjusting the sampling frequency to a first sampling frequency;
And when the current variation is smaller than or equal to the threshold value of the quick charging pile, adjusting the sampling frequency to a second sampling frequency.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring real-time current data output by a charging pile;
the method comprises the steps of obtaining state transition probability differences through a hidden Markov model, optimizing real-time current data, and obtaining initial data;
calculating a noise optimization factor in a hidden state of real-time current data at a preset position in the initial data;
optimizing the real-time current data according to the noise optimization factor to obtain optimized real-time current data, and calculating the current variation according to the optimized real-time current data;
and adjusting the sampling frequency of the current data according to the current variation.
In a preferred embodiment, the computer program when executed by a processor performs the steps of:
calculating a next predicted current monitoring value and a predicted hiding state of the real-time current data, and a next actual monitoring value and a corresponding hiding state;
obtaining the difference between the predicted hidden state transition probability and the actual hidden state transition probability of the next data point according to the next predicted current monitoring value and the predicted hidden state, and the next actual monitoring value and the corresponding hidden state;
Determining the difference between the predicted hidden state transition probability and the actual hidden state transition probability of the next data point as a real-time current data optimization quantity to obtain first initial data;
repeating the steps to obtain the initial data with preset quantity.
In a preferred embodiment, the computer program when executed by a processor performs the steps of:
calculating trend change factors in hidden states of the preset quantity of initial data;
and calculating a noise optimization factor of the initial data according to the trend change factor.
In a preferred embodiment, the computer program when executed by a processor performs the steps of:
calculating the number of data points with consistent directions, the length of a window, the number of continuous changes of the variation, a data point set with consistent directions and a data point difference value;
and obtaining a trend change factor in the hidden state according to the number of data points with consistent directions, the window length, the number of continuous changes of the change quantity, the data point set with consistent directions and the data point difference value.
In a preferred embodiment, the computer program when executed by a processor performs the steps of:
acquiring a trend change factor, a numerical difference distance of a hidden state boundary, a first probability and a second probability;
And calculating to obtain a noise optimization factor of the initial data according to the trend change factor, the numerical difference distance of the hidden state boundary, the first probability and the second probability.
In a preferred embodiment, the computer program when executed by a processor performs the steps of:
when the hidden state is unchanged, obtaining optimized real-time current data according to the noise optimization factor, the actual monitoring value and the state change judgment factor;
and determining the difference value of the optimized real-time current data and the previous real-time current data as the current variation.
In a preferred embodiment, the computer program when executed by a processor performs the steps of:
when the current variation is larger than the threshold value of the quick charging pile, adjusting the sampling frequency to a first sampling frequency;
and when the current variation is smaller than or equal to the threshold value of the quick charging pile, adjusting the sampling frequency to a second sampling frequency.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
The above description of the data acquisition system with adaptive regulation function, the data acquisition device with adaptive regulation function and the storage medium provided by the invention applies specific examples to illustrate the principle and implementation of the invention, and the above examples are only used for helping to understand the method and core ideas of the invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (10)
1. The data acquisition system with the self-adaptive regulation and control function is characterized by comprising the following implementation steps:
acquiring real-time current data output by a charging pile;
the method comprises the steps of obtaining state transition probability differences through a hidden Markov model, optimizing real-time current data, and obtaining initial data;
calculating a noise optimization factor in a hidden state of real-time current data at a preset position in the initial data;
optimizing the real-time current data according to the noise optimization factor to obtain optimized real-time current data, and calculating the current variation according to the optimized real-time current data;
And adjusting the sampling frequency of the current data according to the current variation.
2. The data acquisition system with adaptive regulation and control function according to claim 1, wherein the acquiring the state transition probability difference through the hidden markov model optimizes the real-time current data, and acquires initial data, and the method comprises:
calculating a next predicted current monitoring value and a predicted hiding state of the real-time current data, and a next actual monitoring value and a corresponding hiding state;
obtaining the difference between the predicted hidden state transition probability and the actual hidden state transition probability of the next data point according to the next predicted current monitoring value and the predicted hidden state, and the next actual monitoring value and the corresponding hidden state;
determining the difference between the predicted hidden state transition probability and the actual hidden state transition probability of the next data point as a real-time current data optimization quantity to obtain first initial data;
repeating the steps to obtain the initial data with preset quantity.
3. The data acquisition system with adaptive regulation and control function according to claim 1, wherein the calculating the hidden-state internal noise optimization factor of the real-time current data at the preset position in the initial data includes:
Calculating trend change factors in hidden states of the preset quantity of initial data;
and calculating a noise optimization factor of the initial data according to the trend change factor.
4. A data acquisition system with adaptive regulation and control according to claim 3 wherein said calculating trend change factors within hidden states of a predetermined amount of initial data comprises:
calculating the number of data points with consistent directions, the length of a window, the number of continuous changes of the variation, a data point set with consistent directions and a data point difference value;
and obtaining a trend change factor in the hidden state according to the number of data points with consistent directions, the window length, the number of continuous changes of the change quantity, the data point set with consistent directions and the data point difference value.
5. The data acquisition system with adaptive regulation and control function according to claim 4, wherein the noise optimization factor for obtaining the initial data according to the trend change factor comprises:
acquiring a trend change factor, a numerical difference distance of a hidden state boundary, a first probability and a second probability;
and calculating to obtain a noise optimization factor of the initial data according to the trend change factor, the numerical difference distance of the hidden state boundary, the first probability and the second probability.
6. The data acquisition system with adaptive regulation and control function according to claim 1, wherein the optimizing the real-time current data according to the noise optimizing factor to obtain optimized real-time current data, and calculating the current variation according to the optimized real-time current data comprises:
when the hidden state is unchanged, obtaining optimized real-time current data according to the noise optimization factor, the actual monitoring value and the state change judgment factor;
and determining the difference value of the optimized real-time current data and the previous real-time current data as the current variation.
7. The data acquisition system with adaptive regulation and control function according to claim 1, wherein the adjusting the sampling frequency of the current data according to the current variation comprises:
when the current variation is larger than the threshold value of the quick charging pile, adjusting the sampling frequency to a first sampling frequency;
and when the current variation is smaller than or equal to the threshold value of the quick charging pile, adjusting the sampling frequency to a second sampling frequency.
8. A data acquisition device with adaptive regulation and control function, the device comprising:
The real-time current data acquisition module is used for acquiring real-time current data output when the charging pile is obtained;
the initial data acquisition module is used for optimizing the real-time current data by acquiring the state transition probability difference through the hidden Markov model to acquire initial data;
the noise optimization factor calculation module is used for calculating a noise optimization factor in a hidden state of real-time current data at a preset position in the initial data;
the current variation calculation module is used for optimizing the real-time current data according to the noise optimization factor to obtain optimized real-time current data, and calculating the current variation according to the optimized real-time current data;
and the sampling frequency adjusting module is used for adjusting the sampling frequency of the current data according to the current variation.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of a data acquisition system with adaptive regulation and control function of any one of claims 1 to 7.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of a data acquisition system with adaptive regulation and control function according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310706225.8A CN116449081B (en) | 2023-06-15 | 2023-06-15 | Data acquisition system, device and storage medium with self-adaptive regulation and control function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310706225.8A CN116449081B (en) | 2023-06-15 | 2023-06-15 | Data acquisition system, device and storage medium with self-adaptive regulation and control function |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116449081A true CN116449081A (en) | 2023-07-18 |
| CN116449081B CN116449081B (en) | 2023-08-15 |
Family
ID=87122275
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310706225.8A Active CN116449081B (en) | 2023-06-15 | 2023-06-15 | Data acquisition system, device and storage medium with self-adaptive regulation and control function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116449081B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116757337A (en) * | 2023-08-18 | 2023-09-15 | 克拉玛依市鼎泰建设(集团)有限公司 | House construction progress prediction system based on artificial intelligence |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07283741A (en) * | 1994-04-13 | 1995-10-27 | Fujitsu Ltd | Viterbi decoding method and viterbi decoder |
| JP2000075888A (en) * | 1998-09-01 | 2000-03-14 | Oki Electric Ind Co Ltd | Learning method of hidden markov model and voice recognition system |
| JP2009223443A (en) * | 2008-03-13 | 2009-10-01 | Sony Corp | Learning device, learning method, and program |
| CN101950376A (en) * | 2009-07-09 | 2011-01-19 | 索尼公司 | Hidden Markov model facility for study and method, program and recording medium |
| CN104363653A (en) * | 2014-10-13 | 2015-02-18 | 西北大学 | Passive positioning method for eliminating ambient noise |
| US20150231987A1 (en) * | 2014-02-18 | 2015-08-20 | Energy Pass Incorporation | Adjustment Module and Battery Management System Thereof |
| CN106126910A (en) * | 2016-06-22 | 2016-11-16 | 上海垒土资产管理有限公司 | State Transferring Forecasting Methodology based on Markov state metastasis model and system |
| CN109672579A (en) * | 2017-10-16 | 2019-04-23 | 蔚来汽车有限公司 | Terminal device monitoring data acquisition strategies optimization method and device |
| DE102019103528A1 (en) * | 2018-02-21 | 2019-08-22 | GM Global Technology Operations LLC | METHOD, SYSTEMS AND DEVICES FOR CONTROLLING THE SUPPLYED POWER FOR CONTROLLING A MACHINE |
| CN111756056A (en) * | 2020-07-14 | 2020-10-09 | 电子科技大学 | Parameter self-adaptive virtual synchronous generator prediction control method |
| CN114720764A (en) * | 2022-02-23 | 2022-07-08 | 江苏森维电子有限公司 | Harmonic analysis method and system based on real-time monitoring data of electric meter |
-
2023
- 2023-06-15 CN CN202310706225.8A patent/CN116449081B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07283741A (en) * | 1994-04-13 | 1995-10-27 | Fujitsu Ltd | Viterbi decoding method and viterbi decoder |
| JP2000075888A (en) * | 1998-09-01 | 2000-03-14 | Oki Electric Ind Co Ltd | Learning method of hidden markov model and voice recognition system |
| JP2009223443A (en) * | 2008-03-13 | 2009-10-01 | Sony Corp | Learning device, learning method, and program |
| CN101950376A (en) * | 2009-07-09 | 2011-01-19 | 索尼公司 | Hidden Markov model facility for study and method, program and recording medium |
| US20150231987A1 (en) * | 2014-02-18 | 2015-08-20 | Energy Pass Incorporation | Adjustment Module and Battery Management System Thereof |
| CN104363653A (en) * | 2014-10-13 | 2015-02-18 | 西北大学 | Passive positioning method for eliminating ambient noise |
| CN106126910A (en) * | 2016-06-22 | 2016-11-16 | 上海垒土资产管理有限公司 | State Transferring Forecasting Methodology based on Markov state metastasis model and system |
| CN109672579A (en) * | 2017-10-16 | 2019-04-23 | 蔚来汽车有限公司 | Terminal device monitoring data acquisition strategies optimization method and device |
| DE102019103528A1 (en) * | 2018-02-21 | 2019-08-22 | GM Global Technology Operations LLC | METHOD, SYSTEMS AND DEVICES FOR CONTROLLING THE SUPPLYED POWER FOR CONTROLLING A MACHINE |
| CN111756056A (en) * | 2020-07-14 | 2020-10-09 | 电子科技大学 | Parameter self-adaptive virtual synchronous generator prediction control method |
| CN114720764A (en) * | 2022-02-23 | 2022-07-08 | 江苏森维电子有限公司 | Harmonic analysis method and system based on real-time monitoring data of electric meter |
Non-Patent Citations (2)
| Title |
|---|
| 傅伟 等: "基于小波域隐马尔可夫树模型的医学图像去噪", 《 医疗卫生装备》, vol. 31, no. 1, pages 34 - 36 * |
| 廉玉波 等: "基于混合高斯-隐马尔可夫模型的动力电池实时热失控检测", 《汽车工程》, vol. 45, no. 1, pages 139 - 146 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116757337A (en) * | 2023-08-18 | 2023-09-15 | 克拉玛依市鼎泰建设(集团)有限公司 | House construction progress prediction system based on artificial intelligence |
| CN116757337B (en) * | 2023-08-18 | 2023-11-21 | 克拉玛依市鼎泰建设(集团)有限公司 | House construction progress prediction system based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116449081B (en) | 2023-08-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116994416B (en) | Fan operation fault early warning method and system based on artificial intelligence | |
| CN116449081B (en) | Data acquisition system, device and storage medium with self-adaptive regulation and control function | |
| CN116306798A (en) | Ultra-short time wind speed prediction method and system | |
| CN112036051B (en) | Method, device, equipment and medium for predicting residual service life of magnetic suspension system | |
| US7949497B2 (en) | Machine condition monitoring using discontinuity detection | |
| CN116086537A (en) | Equipment state monitoring method, device, equipment and storage medium | |
| CN111460639A (en) | Method and device for dynamically calculating temperature of cable conductor, electronic equipment and storage medium | |
| CN118170004B (en) | Control method and system based on Internet of things | |
| CN109116244A (en) | A kind of judgment method and device of power battery aging tendency | |
| CN111971200A (en) | Method for determining the state of ageing of a battery, computer program, storage device, control device and vehicle | |
| CN116992311B (en) | Energy storage power supply state analysis method based on machine learning | |
| CN116804695A (en) | Cable state determining method and device based on historical fault event | |
| US7797129B2 (en) | Processing data to maintain an estimate of a running median | |
| CN117233629A (en) | Method, system, equipment and medium for testing electrical performance of lithium ion battery | |
| CN117250520B (en) | Safety analysis and evaluation method and system for large-scale battery energy storage power station | |
| CN113339208A (en) | Method for selecting abnormal vibration fragments of wind turbine generator | |
| CN115112962A (en) | Non-invasive load identification method, system, storage medium and equipment | |
| CN117706367B (en) | Echelon battery performance determining method and related device | |
| CN117972620B (en) | Cell abnormality prediction method and device based on logistic regression algorithm | |
| EP4449141A1 (en) | A computer implemented method and a system for determining electromotive force curves of a battery | |
| Jensen et al. | Remaining useful life estimation of stator insulation using particle filter | |
| CN116413626B (en) | Evaluation method for battery aging state, electronic equipment and storage medium | |
| CN118091325B (en) | Intelligent cable detection method and system | |
| CN117970128B (en) | Battery comprehensive experiment debugging method and system based on real-time feedback control | |
| CN113514148B (en) | Equipment vibration early warning method and system based on low-delay data smoothing |
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 |