Parameter prediction method and device, electronic equipment and computer program product
By obtaining the state parameter difference, time constant and influencing factor between known points and unknown points, the problem of inaccurate prediction of the state parameters of unknown points is solved, high-accuracy parameter prediction is achieved, and sensor costs are saved.
Patent Information
- Application Number
- CN202510921745.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-04
- Publication Date
- 2025-10-10
AI Technical Summary
In the prior art, the prediction accuracy of the state parameters of unknown points is not high because the state parameter differences, time constants and influencing factors between known and unknown points are not effectively utilized.
By measuring the current and historical state parameters of known points, the state parameter difference, time constant and influencing factor are obtained. Based on these parameters, the state parameters of unknown points are predicted, taking into account the working conditions and external influences of the equipment under test.
The prediction accuracy of unknown point state parameters is improved, the cost of sensor hardware is saved, and there is no need to change the equipment structure.
Smart Images
Figure CN120762372A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of industrial control technology, and in particular relates to a parameter prediction method, a parameter prediction device, an electronic device, and a computer program product. Background Art
[0002] Industrial equipment often requires real-time monitoring of the state parameters of certain points. However, due to limitations in the physical size, structure, cost, and assembly of industrial equipment, it is often not possible to install sensors at every measurement point. Currently, a common solution is to predict the state parameters of unknown points based on the state parameters of known points. However, this approach often assumes that the difference between the state parameters of the known and unknown points is a fixed value, resulting in low accuracy in the prediction of the state parameters of the known points. Summary of the Invention
[0003] The present application provides a parameter prediction method, a parameter prediction device, an electronic device and a computer program product, which can improve the accuracy of parameter prediction for unknown points.
[0004] In a first aspect, the present application provides a parameter prediction method, comprising:
[0005] In the prediction stage, current state parameters and historical state parameters of known points of the device under test are obtained by measurement, wherein the number of the historical state parameters is at least one;
[0006] Obtain the difference in state parameters between the known point and the unknown point of the device under test in steady state;
[0007] Obtain the time constant of the device under test for the state parameters;
[0008] Determining an influence value of a preset influencing factor on the state parameter, wherein the preset influencing factor is determined based on the state parameter and the operating condition of the device under test in the prediction phase;
[0009] Based on the current state parameters, historical state parameters, state parameter differences, impact values and time constants, the current state parameters of unknown points of the device under test are predicted.
[0010] In a second aspect, the present application provides a parameter prediction device, comprising:
[0011] A measurement module is used to obtain, during the prediction phase, current state parameters and historical state parameters of a known point of the device under test by measurement, wherein the number of the historical state parameters is at least one;
[0012] A first acquisition module is used to obtain the difference in state parameters between a known point and an unknown point of the device under test in a steady state;
[0013] The second acquisition module is used to obtain the time constant of the device under test for the state parameter;
[0014] A first determination module is configured to determine an influence value of a preset influence factor on a state parameter, wherein the preset influence factor is determined based on the state parameter and an operating condition of the device under test in a prediction phase;
[0015] The prediction module is used to predict the current state parameters of the unknown points of the device under test based on the current state parameters, historical state parameters, state parameter differences, influence values and time constants.
[0016] In a third aspect, the present application provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method according to the first aspect are implemented.
[0017] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method of the first aspect are implemented.
[0018] In a fifth aspect, the present application provides a computer program product, which includes a computer program. When the computer program is executed by one or more processors, it implements the steps of the method of the first aspect.
[0019] Compared to the prior art, the present invention offers the following advantages: When predicting the state parameters of an unknown point, the present invention no longer solely considers the steady-state state parameter difference between the known and unknown points. Instead, it also considers the time constant of the device under test with respect to the state parameter, as well as the influence of a preset influencing factor on the state parameter. It is understood that the time constant can reflect the speed at which the device under test reacts to changes in the state parameter; the preset influencing factor is determined based on the state parameter and the operating conditions of the device under test during the prediction phase, and can reflect the external influences on the state parameter of the device under test during the prediction phase, thereby quantifying these external influences and obtaining the influence value of the state parameter. Furthermore, the current state parameter and historical state parameter of the known point can be used to determine whether the state parameter of the device under test has reached equilibrium, and possible measurement errors and interference can also be eliminated. Ultimately, based on the obtained current state parameter, historical state parameter, state parameter difference, influence value, and time constant, the electronic device can more accurately predict the current state parameter of the unknown point of the device under test. This process does not require any changes to the structure of the device under test, saves the cost of related sensor hardware, and improves the accuracy of parameter prediction for unknown points.
[0020] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0022] Figure 1 Schematic diagram of the implementation process of the parameter prediction method provided in the embodiment of the present application;
[0023] Figure 2 This is a structural block diagram of a parameter prediction device provided in an embodiment of the present application;
[0024] Figure 3 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0025] The following embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application and are therefore only examples and are not intended to limit the scope of protection of the present application.
[0026] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.
[0027] In the description of the embodiments of the present application, technical terms such as "first" and "second" are only used to distinguish different objects and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features.
[0028] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0029] In the description of the embodiments of this application, the term "and / or" is simply a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.
[0030] In the description of the embodiments of the present application, the term "plurality" refers to two or more (including two), unless otherwise clearly and specifically defined.
[0031] The embodiment of the present application proposes a parameter prediction method. Among them, the parameter prediction method can be applied to electronic devices. In some examples, the electronic device can be a computer, a mobile phone or any other device with data processing capabilities, and the specific type of the electronic device is not limited here. The electronic device can establish a communication connection with the device under test, so as to directly obtain the measurement results of the various sensors integrated in the device under test, wherein the device under test is the device that has parameter prediction requirements in the embodiment of the present application. In some examples, the device under test can be an industrial device, such as an industrial switch. Of course, the electronic device may not establish a communication connection with the device under test, and the user manually inputs the measurement results of the various sensors integrated in the device under test into the device under test, and the connection relationship between the electronic device and the device under test is not limited here. In actual application scenarios, the parameter prediction method proposed in the embodiment of the present application can be used to predict various state parameters separately, including but not limited to temperature and air pressure, etc., which are not limited here. Please refer to Figure 1 , Figure 1 The implementation process of the parameter prediction method applied to the electronic device is given, and the details are as follows:
[0032] Step 101 , in the prediction stage, obtain current state parameters and historical state parameters of known points of the device under test through measurement.
[0033] To implement the solution proposed in the embodiments of this application, the device under test can first be divided into a calibration phase and a prediction phase. The calibration phase is the preliminary preparation phase, which mainly calibrates the relevant data required for prediction; the prediction phase is the stage during the application process where prediction is actually performed, and it mainly performs predictions based on the relevant data obtained from calibration and the data currently measured in the prediction phase.
[0034] In the prediction stage, the electronic device can obtain the state parameters of the known points of the device to be tested through measurement. The known point refers to a location point where a corresponding sensor is installed (or set), that is, the state parameters of the known point can be directly obtained by measuring the corresponding sensor. It can be understood that the purpose of the parameter prediction method proposed in the embodiment of the present application is to predict the state parameters of the unknown point through the state parameters of the known point. The unknown point refers to a location point where a corresponding sensor is not installed (or set). It should be noted that there can be multiple known points and multiple unknown points.
[0035] An electronic device can obtain multiple state parameters of a known point on a device under test through measurement. These state parameters are measured at different times. Generally speaking, these state parameters can be divided into: a state parameter at the current moment (referred to as the current state parameter) and a state parameter at at least one historical moment (referred to as the historical state parameter). The current and historical state parameters can be used to understand the dynamic change trend of the device, laying the foundation for subsequent prediction of the state parameters of unknown points.
[0036] Step 102: Obtain the difference in state parameters between the known point and the unknown point of the device under test in a steady state.
[0037] Among them, steady state refers to the state in which the device under test has been running stably; in steady state, the state parameters of each position point of the device under test have reached equilibrium, and generally no longer change when external factors do not change. Accordingly, the embodiment of the present application can also record the non-steady state as transient state; in transient state, the state parameters of each position point of the device under test have not reached equilibrium, which is generally affected by external factors. It can be understood that the state parameter difference can be obtained and stored in the storage space of the electronic device during the calibration stage of the device under test. During the prediction stage of the device under test, the electronic device only needs to directly read its storage space to obtain the stored state parameter difference. The state parameter difference can be used as a stable reference value in the prediction stage, thereby achieving accurate prediction of unknown points in the prediction stage.
[0038] Step 103: Obtain the time constant of the device under test with respect to the state parameter.
[0039] Among them, the time constant refers to the speed of response of the device under test to the change of state parameters caused by external factors; in the embodiment of the present application, the time constant can be approximately regarded as the inertia of the device under test with respect to the state parameters. In the embodiment of the present application, the electronic device can obtain the time constant through modeling, thereby introducing the physical response characteristics of the device under test and improving the credibility of the modeling during subsequent predictions. It can be understood that the time constant can be obtained through modeling during the calibration stage of the device under test and stored in the storage space of the electronic device. During the prediction stage of the device under test, the electronic device only needs to directly read its storage space to obtain the stored time constant.
[0040] In some embodiments, the time constant of the device under test's state parameter may change as the device ages or as the environment in which it is used changes. In this regard, in embodiments of the present application, an update mechanism may be considered to periodically update the time parameter and always store the latest time parameter, thereby further ensuring the accuracy of subsequent prediction stages.
[0041] Step 104: Determine the impact value of the preset impact factor on the state parameter.
[0042] In the prediction stage, some external factors can also be considered. It is understandable that different working conditions may have different influencing factors. In addition, different types of state parameters may also have different influencing factors. For example, when the state parameter to be predicted is temperature, the influencing factors that need to be considered may include fill light, etc.; but when the state parameter to be predicted is of other types, such as air pressure, the influencing factors that need to be considered do not need to include fill light, etc. In actual application scenarios, different influencing factors will contribute to the changes in state parameters to varying degrees; based on this, the embodiment of the present application can determine the influencing factors that adapt to the current scenario based on the specific working conditions of the device to be tested in the prediction stage and the current state parameters to be predicted, and analyze the impact values of these influencing factors on the state parameters, that is, how these influencing factors will affect the state parameters of unknown points.
[0043] In some embodiments, the influence value of the influencing factor on the state parameter can be specifically determined by two parts, namely: the maximum influence value of the influencing factor on the state parameter, and the weight of the influencing factor. In fact, the weights of the various influencing factors can form a weight matrix. It can be understood that both of the above can be obtained through modeling during the calibration phase of the device under test and stored in the storage space of the electronic device. During the prediction phase of the device under test, the electronic device only needs to directly read its storage space. Afterwards, based on the maximum influence value and the weight, the electronic device can calculate the influence value, specifically for each influencing factor, calculate the product between the maximum influence value of the influencing factor on the state parameter and the weight of the influencing factor; after adding up each of the obtained products, the influence value of the influencing factor on the state parameter can be obtained.
[0044] Step 105 : predicting the current state parameters of the unknown points of the device under test based on the current state parameters, historical state parameters, state parameter differences, impact values, and time constants.
[0045] It can be seen that during the prediction stage, electronic equipment can obtain the changing trend of state parameters, the baseline value during prediction, the dynamic response based on modeling, and the impact of external influencing factors on state parameters through the above steps; all of the above data can be used as relevant inputs for parameter prediction, and the current state parameters of the unknown points of the device under test can be predicted through the formula obtained by modeling.
[0046] In some implementations, the electronic device may determine the state parameter difference by:
[0047] A1. During the calibration phase, the state parameters of the known points of the device under test are monitored.
[0048] During the calibration phase, the electronic device can read the sensors corresponding to known points on the device under test in real time or periodically, thereby monitoring the state parameters of these known points. Since a key requirement for steady-state performance is that the state parameters at each location remain stable, the electronic device can continuously track the changes in the state parameters of each known point to determine whether the device under test is currently in steady state or transient state.
[0049] A2. When the state parameters of the known points remain unchanged within a preset monitoring period, the state parameter difference is calculated based on the state parameters of the known points and the state parameters of the unknown points.
[0050] When the state parameters of each known point remain unchanged for the preset monitoring period, it is preliminarily considered that the system has entered a steady state. At this point, the difference in state parameters between any known point and any unknown point should be a constant. Based on this, the difference in state parameters can be calculated based on the state parameters of each known point and the state parameters of each unknown point. The state parameters of the unknown points during the calibration phase can be obtained through special means; for example, if the state parameter is temperature, the temperature of the unknown point during the calibration phase can be measured using a thermocouple probe or other means, which is not limited here.
[0051] In some embodiments, the electronic device may determine the time constant by:
[0052] B1. During the calibration phase, the difference between the state parameters of the known points and the unknown points of the device under test is monitored.
[0053] Based on the previous description of the calibration phase, it can be known that during the calibration phase, the electronic device can read the sensor corresponding to the known point of the device under test in real time or periodically, thereby realizing the monitoring of the state parameters of the known point. In addition, through special means, such as thermocouple probes and other means, the state parameters of the unknown point can also be measured in real time or periodically during the calibration phase, thereby realizing the monitoring of the state parameters of the known point. After the measured data are aligned in time sequence, the difference between the state parameters of the known point and the state parameters of the unknown point can be obtained. It should be noted that this specifically refers to the monitoring of the difference when the device under test is in a transient state. The reason is that if the device under test is in a steady state, the difference between the state parameters of the known point and the state parameters of the unknown point has become stable, and the subsequent difference time curve cannot be obtained.
[0054] B2. Draw a difference-time curve based on the relationship between the difference and time.
[0055] The electronic device can associate the difference between the state parameters of the known point and the state parameters of the unknown point with the corresponding time sequence point, thereby obtaining the relationship between the difference and time, and then plotting a difference time curve. It can be understood that the horizontal axis of the difference time curve represents time (i.e., the time sequence point) and the vertical axis represents the difference.
[0056] B3. Perform exponential fitting on the difference time curve.
[0057] The electronic device can perform exponential fitting on the difference time curve using a preset fitting method. In some examples, the fitting method can be least squares exponential fitting; of course, other fitting methods can also be used, which are not limited here. When least squares exponential fitting is used, the following relevant parameters are involved: fitting coefficient b, time t, natural constant e, and time constant c.
[0058] B4. Determine the time constant based on the fitting results.
[0059] Electronic devices are being ct After fitting using the least squares exponential fitting method, the time constant c can be determined accordingly. This time constant c can be stored in the storage space of the electronic device for subsequent prediction.
[0060] To facilitate understanding of the present embodiment, the specific modeling process involved in parameter prediction is described below.
[0061] On the one hand, electronic equipment can perform correlation analysis on influencing factors, specifically:
[0062] During the calibration phase, when the device under test has entered a steady state for its state parameters, the electronic device can, based on the measurement accuracy requirements and the Laida principle (also known as the 3σ principle), screen out the influencing factors that will affect the state parameters in the steady state by more than 3 times the accuracy when turned on or off; then, based on the normalization method of different dimensions, the electronic device can confirm the weight of each influencing factor, thereby obtaining a weight matrix. Through this weight matrix, the electronic device can weight the influence of each influencing factor on the state parameter, which can be specifically expressed by the following formula (1):
[0063]
[0064] In the above formula (1), Y i It represents the state parameter of the i-th known point in steady state; W j represents the state parameter of the jth unknown point in steady state; A is the difference between the state parameters of the known point and the measured point of the device under test in steady state; x m represents the maximum impact value of the mth influencing factor on the state parameter, where the total number of influencing factors is n; Q m is the weight of the mth influencing factor (specifically the normalized weight).
[0065] In some examples, taking the state parameter as temperature, the weight of the mth influencing factor can be expressed as Among them, I qm is the parameter that affects the temperature rise of this factor, I qm _max is the maximum value of the parameter corresponding to this factor. Taking the fill light as an example, assuming that when the device does not turn on the fill light, the temperature difference between the known point and the measured point is A, and the total impact of the fill light on the temperature difference between the known point and the measured point when it is turned off and on is x1. When the current of the fill light is adjustable, according to the properties of the fill light, the current can be used to measure the degree of heating of the fill light, so the weight of the fill light is When the current of the fill light is not adjustable, if the fill light is always on, then Q补 =1, if the fill light is normally off, then Q 补 =0.
[0066] On the other hand, during the calibration phase, when the state parameters of the device under test have entered a transient state, the state parameters of the known points and unknown points of the device under test change with time t (t = 0 represents the initialization moment, such as the moment when the device under test is powered on), and the difference between the two is not fixed. The above changes may be caused by the device under test being in the power-on startup phase, or by changes in influencing factors (for example, when the state parameter is temperature, the turn-on or turn-off of the heat source such as the fill light / fan / heating wire of the device under test), which will not be elaborated here. Based on this, the embodiment of the present application proposes a dynamic correction compensation for the change of state parameters under transient state, specifically: based on the change of state parameters of known points, the change of state parameters of unknown points is dynamically corrected and compensated. The above dynamic correction compensation can be expressed as a transient model, which can be represented by the following formula (2):
[0067]
[0068] In the above formula (2), Y i (t) indicates transient state, Y i Function that changes with time t, Y i This has been explained in the previous article and will not be repeated here; j (t) represents transient state, W j Function that changes with time t, W j As explained above, I will not repeat it here. X(t) is the correction function, which can be fitted to the exponential be after least square exponential fitting. ct , where b, e, c and t have been explained above and will not be repeated here.
[0069] Based on the above formula (2), we can know that in transient state, Y i (t) and W j (t) is not a constant value, but changes gradually with time t until it reaches a steady state; therefore, the above formula (1) is only valid in a steady state and no longer valid in a transient state. The transient model is updated to the above formula (2). It can be understood that the introduction of X(t) in the above formula (2) is essentially equivalent to the real-time correction and adjustment of Y i (t), so that the above formula (1) also holds true in transient state.
[0070] However, in some scenarios, the state of the device under test before power-on may be unknown, such as when the device under test is cold-started and then powered on after reaching thermal equilibrium. i (t) and W jThe curves of (t) changing with t are different. For these scenarios, it may be difficult to obtain the formula of X(t) by fitting. To this end, the expression of X(t) can be further derived. Specifically, by shifting the terms in the above formula (2), it can be expressed as the following formula (3):
[0071]
[0072] It can be understood that the above formula increases with Y i (t) and W j After taking the derivative of both sides of the above formula (3), we can get the following formula (4):
[0073] X ′ (t) = W ′ j (t)-Y ′ i (t)(4)
[0074] In the physical model of actual state parameters, the response speed of the state parameters of the known points (equivalent to the rate of change of the state parameters, that is, the slope) is usually much greater than that of the unknown points, that is, W ′ j (t) is much smaller than Y ′ i (t). Therefore, the above formula (4) can be simplified as:
[0075] X ′ (t) = -Y ′ i (t)(5)
[0076] Since the correction function X(t) can be fitted as an exponential be ct , combined with the definition formula of differential, the above formula (4) can be rewritten as:
[0077]
[0078] After deducing based on the above formula (6), it can be seen that the correction function X(t) can be expressed as the following formula (7):
[0079]
[0080] The physical connotation expressed by the above formula (7) is specifically: the rate of change Y of the correction function X(t) and the state parameter of the known point ′ i (t) has a linear relationship. Based on the above formula (7), the above formula (2) is rewritten to express the state parameters of the unknown point under transient state as the following formula (8):
[0081]
[0082] In the above formula (8), It can be regarded as a correction factor, which can be used to express the degree of influence of the change of the state parameter of the known point on the state parameter difference; in other words, the degree of influence can be expressed by the slope of the parameter change of the known point.
[0083] Based on the above model establishment process, it can be seen that the difference between the state parameters of the known point and the unknown point in the transient process has a linear relationship with the rate of change of the state parameters of the known point, that is, Linear correlation. Therefore, in the prediction stage, this linear relationship can be used to obtain the slope of the state parameters of the known point by obtaining the deviation of the state parameters of the known point at adjacent moments, thereby correcting the state parameters of the known point to achieve the effect of eliminating transient deviations and ensuring that the temperature of the unknown point can also be predicted with high accuracy during transient conditions.
[0084] In some embodiments, based on the above formula (8) proposed in the modeling process, it can be seen that the difference between the state parameters of the known point and the unknown point changes continuously with time t during the transient process. However, in actual application scenarios, in the prediction stage, the sampling time of the device under test cannot be infinitely small. Therefore, in order to apply the above formula (8), the above formula (8) needs to be discretized. Specifically, the discretization process consists of two parts, namely the calibration of the time constant c and the discretization of Δt, which are described in detail below:
[0085] The specific calibration of the time constant c is as follows: the averaging method can be used, and the above formula (8) can be expressed as the following formula (9):
[0086]
[0087] Δt is the sampling time interval; as an example only, it can be the minimum sampling time interval of the device under test. During the calibration phase, the state parameters of the known point at N times can be continuously obtained, and the corresponding time constants can be calculated and averaged to serve as the actual time constant c. Then, the above equation (9) can be further optimized to the following equation (10):
[0088]
[0089] The discretization of Δt is specifically as follows: in order to reduce the sampling error, multiple samples can be sampled and recorded, and then the average value is taken for calculation. Then, step 101 can be optimized as follows: in the prediction stage, the electronic device can measure the state parameters of the known point based on the preset time interval, thereby obtaining the current state parameters measured at the current moment, and the historical state parameters measured at at least one historical moment (for example, 3 historical moments). It can be understood that in this way, for the same known point, the sampling time intervals of the two adjacent state parameters in the time series are consistent, and both can be Δt. Taking the state parameter as temperature and t as the current moment as an example, then Y t It can be used to represent the temperature of a known point. In addition, based on the sampling time interval, the temperature of the known point is obtained at t1, t2 and t3 before the current moment, and Y1, Y2 and Y3 can be obtained. The correction factor can be expressed as It can be understood that when the device under test reaches a steady state, the state parameters of the known points no longer change, and the correction factor is 0, and will not be involved in subsequent calculations.
[0090] Taking into account the influencing factors, the transient state of the device under test, and the sampling error in the measurement phase, combined with the derivation of formulas (1) to (10) proposed above, the state parameter prediction formula used in the prediction phase can be specifically shown in the following formula (11):
[0091]
[0092] Based on equation (11), the electronic device can first calculate a correction factor based on the current state parameters and historical state parameters. This correction factor is used to express the parameter change slope of the known point. Then, the current state parameter, the correction factor, the read state parameter difference, the read influence value, and the read time constant are substituted into equation (11) to calculate the current state parameter of the unknown point of the device under test.
[0093] As can be seen from the above, in the embodiments of the present application, when predicting the state parameters of an unknown point, the difference between the state parameters of the known and unknown points in the steady state is no longer considered alone. Instead, the time constant of the device under test with respect to the state parameter, as well as the influence of the preset influence factor on the state parameter, are also considered. It is understood that the time constant can reflect the speed at which the device under test reacts to changes in the state parameter; the preset influence factor is determined based on the state parameter and the operating conditions of the device under test during the prediction phase, and can reflect the external influence on the state parameter of the device under test during the prediction phase, thereby quantifying the external influence and obtaining the influence value of the state parameter. In addition, the current state parameter and historical state parameter of the known point can be used to determine whether the state parameter of the device under test has reached equilibrium, and possible measurement errors and interference can also be eliminated. Ultimately, based on the obtained current state parameter, historical state parameter, state parameter difference, influence value, and time constant, the electronic device can make a relatively accurate prediction of the current state parameter of the unknown point of the device under test. The above process does not require changing the structure of the device under test, also saves the cost of related sensor hardware, and can achieve improved accuracy in parameter prediction of unknown points.
[0094] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.
[0095] Corresponding to the parameter prediction method provided above, the embodiment of the present application also provides a parameter prediction device. Figure 2 , the parameter prediction device 2 in the embodiment of the present application includes:
[0096] The measurement module 201 is configured to obtain, during the prediction phase, current state parameters and historical state parameters of a known point of the device under test through measurement, wherein the number of the historical state parameters is at least one;
[0097] A first acquisition module 202 is used to obtain a state parameter difference between a known point and an unknown point of the device under test in a steady state;
[0098] The second acquisition module 203 is used to obtain the time constant of the device under test for the state parameter;
[0099] A first determining module 204 is configured to determine an influence value of a preset influencing factor on a state parameter, wherein the preset influencing factor is determined based on the state parameter and the operating condition of the device under test in the prediction phase;
[0100] The prediction module 205 is used to predict the current state parameters of the unknown points of the device under test based on the current state parameters, historical state parameters, state parameter differences, impact values and time constants.
[0101] In some embodiments, the measuring module 201 is specifically configured to measure the state parameter of the known point based on a preset time interval to obtain a current state parameter measured at a current time and a historical state parameter measured at at least one historical time during the prediction stage.
[0102] In some embodiments, the parameter prediction apparatus 2 further comprises:
[0103] a first monitoring module configured to monitor the state parameter of the known point of the to-be-tested device during the calibration stage;
[0104] a calculating module configured to calculate the state parameter difference based on the state parameter of the known point and the state parameter of the unknown point when the state parameter of the known point remains unchanged within a preset monitoring duration.
[0105] In some embodiments, the parameter prediction apparatus 2 further comprises:
[0106] a second monitoring module configured to monitor the difference between the state parameter of the known point and the state parameter of the unknown point of the to-be-tested device during the calibration stage;
[0107] a drawing module configured to draw a difference-time curve according to the relationship between the difference and time;
[0108] a fitting module configured to perform exponential fitting on the difference-time curve;
[0109] a second determining module configured to determine the time constant according to the fitting result.
[0110] In some embodiments, the first determining module 204 comprises:
[0111] a first obtaining unit configured to obtain a maximum influence value of each influence factor on the state parameter;
[0112] a second obtaining unit configured to obtain a weight of each influence factor;
[0113] a first calculating unit configured to calculate the influence value according to the maximum influence value and the weight.
[0114] In some embodiments, the prediction module 205 comprises:
[0115] a second calculating unit configured to calculate a correction factor based on the current state parameter and the historical state parameter, the correction factor being used to express a parameter change slope of the known point;
[0116] a third calculating unit configured to calculate the current state parameter of the unknown point of the to-be-tested device based on the current state parameter, the correction factor, the state parameter difference, the influence value, the time constant and a preset state parameter prediction formula.
[0117] In some embodiments, the state parameter includes temperature or air pressure.
[0118] As can be seen from the above, in the embodiment of the present application, when predicting the state parameters of an unknown point, the parameter prediction device no longer only considers the difference in state parameters between the known and unknown points in steady state, but also considers the time constant of the device under test with respect to the state parameter, as well as the influence value of the preset influence factor on the state parameter. It can be understood that the time constant can reflect the reaction speed of the device under test to changes in the state parameter; the preset influence factor is determined based on the state parameter and the operating conditions of the device under test during the prediction phase, and can reflect the external influence on the state parameter of the device under test during the prediction phase, thereby quantifying the external influence and obtaining the influence value of the state parameter. In addition, the current state parameter and historical state parameter of the known point can be used to determine whether the state parameter of the device under test has reached equilibrium, and possible measurement errors and interference can also be eliminated. Ultimately, based on the obtained current state parameter, historical state parameter, state parameter difference, influence value, and time constant, the parameter prediction device can make a relatively accurate prediction of the current state parameter of the unknown point of the device under test. The above process does not require changing the structure of the device under test, also saves the relevant sensor hardware cost, and can achieve improved accuracy in parameter prediction of unknown points.
[0119] Corresponding to the parameter prediction method provided above, the embodiment of the present application further provides an electronic device. Figure 3 The electronic device 3 in the embodiment of the present application includes: a memory 301, one or more processors 302 ( Figure 3 Only one is shown in the figure) and a computer program stored in the memory 301 and executable on the processor. Specifically, the processor 302 implements the following steps when executing the computer program stored in the memory 301:
[0120] In the prediction stage, current state parameters and historical state parameters of known points of the device under test are obtained by measurement, wherein the number of the historical state parameters is at least one;
[0121] Obtain the difference in state parameters between the known point and the unknown point of the device under test in steady state;
[0122] Obtain the time constant of the device under test for the state parameters;
[0123] Determining an influence value of a preset influencing factor on the state parameter, wherein the preset influencing factor is determined based on the state parameter and the operating condition of the device under test in the prediction phase;
[0124] Based on the current state parameters, historical state parameters, state parameter differences, impact values and time constants, the current state parameters of unknown points of the device under test are predicted.
[0125] Assuming that the above is the first possible implementation, in a second possible implementation provided on the basis of the first possible implementation, in the prediction stage, current state parameters and historical state parameters of known points of the device under test are obtained by measurement, including:
[0126] In the prediction stage, the state parameters of the known points are measured based on preset time intervals to obtain the current state parameters measured at the current moment and the historical state parameters measured at at least one historical moment.
[0127] In a third possible implementation provided on the basis of the second possible implementation, the state parameter difference is determined in the following manner:
[0128] During the calibration phase, the state parameters of known points of the device under test are monitored;
[0129] When the state parameters of the known points remain unchanged within a preset monitoring period, the state parameter difference is calculated based on the state parameters of the known points and the state parameters of the unknown points.
[0130] In a fourth possible implementation provided on the basis of the first possible implementation, the time constant is determined by:
[0131] During the calibration phase, the difference between the state parameters of the known points and the unknown points of the device under test is monitored;
[0132] Draw a difference time curve based on the relationship between the difference and time;
[0133] Exponential fitting was performed on the difference time curve;
[0134] Based on the fitting results, the time constant is determined.
[0135] In a fifth possible implementation provided on the basis of the first possible implementation, determining the influence value of the preset influencing factor on the state parameter includes:
[0136] Obtain the maximum impact value of each influencing factor on the state parameter;
[0137] Get the weight of each impact factor;
[0138] Calculate the influence value based on the maximum influence value and weight.
[0139] In a sixth possible implementation provided on the basis of the first possible implementation, predicting the current state parameters of unknown points of the device under test based on the current state parameters, historical state parameters, state parameter differences, influence values, and time constants includes:
[0140] Calculate the correction factor based on the current state parameters and historical state parameters. The correction factor is used to express the parameter change slope of the known point.
[0141] Based on the current state parameters, correction factors, state parameter differences, impact values, time constants, and preset state parameter prediction formulas, the current state parameters of unknown points of the device under test are calculated.
[0142] In the seventh possible implementation provided based on the first possible implementation, or the second possible implementation, or the third possible implementation, or the fourth possible implementation, or the fifth possible implementation, or the sixth possible implementation, the state parameters include: temperature or air pressure.
[0143] It should be understood that in the embodiment of the present application, the processor 302 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.
[0144] The memory 301 may include a read-only memory and a random access memory, and provides instructions and data to the processor 302. A portion or all of the memory 301 may also include a non-volatile random access memory. For example, the memory 301 may also store device type information.
[0145] As can be seen from the above, in the embodiments of the present application, when predicting the state parameters of an unknown point, the difference between the state parameters of the known and unknown points in the steady state is no longer considered alone. Instead, the time constant of the device under test with respect to the state parameter, as well as the influence of the preset influence factor on the state parameter, are also considered. It is understood that the time constant can reflect the speed at which the device under test reacts to changes in the state parameter; the preset influence factor is determined based on the state parameter and the operating conditions of the device under test during the prediction phase, and can reflect the external influence on the state parameter of the device under test during the prediction phase, thereby quantifying the external influence and obtaining the influence value of the state parameter. In addition, the current state parameter and historical state parameter of the known point can be used to determine whether the state parameter of the device under test has reached equilibrium, and possible measurement errors and interference can also be eliminated. Ultimately, based on the obtained current state parameter, historical state parameter, state parameter difference, influence value, and time constant, the electronic device can make a relatively accurate prediction of the current state parameter of the unknown point of the device under test. The above process does not require changing the structure of the device under test, also saves the cost of related sensor hardware, and can achieve improved accuracy in parameter prediction of unknown points.
[0146] An embodiment of the present application further provides a computer program product. When the computer program product is run on an electronic device, the electronic device can implement the steps in the above-mentioned various method embodiments.
[0147] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the above-mentioned device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0148] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.
[0149] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of external device software and electronic hardware. Whether the functions are realized in hardware or software manner depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.
[0150] In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented by other ways. For example, the system embodiments described above are only illustrative. For example, the division of the above modules or units is only a logical function division. In actual implementation, there can be another division manner. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
[0151] The units described above as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.
[0152] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the associated hardware through a computer program. The above-mentioned computer program can be stored in a computer-readable storage medium, and the computer program, when executed by the processor, can implement the steps of the above-mentioned various method embodiments. Among them, the above-mentioned computer program includes computer program code, and the above-mentioned computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The above-mentioned computer-readable storage medium may include: any entity or device that can carry the above-mentioned computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer-readable memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the above-mentioned computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable storage media does not include electrical carrier signals and telecommunication signals.
[0153] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.
Claims
1. A parameter prediction method, characterized in that: include: In the prediction stage, current state parameters and historical state parameters of known points of the device under test are obtained by measurement, wherein the number of the historical state parameters is at least one; Obtaining a state parameter difference between the known point and the unknown point of the device under test in a steady state; Obtaining a time constant of the device under test with respect to a state parameter; Determining an influence value of a preset influence factor on the state parameter, wherein the preset influence factor is determined based on the state parameter and the operating condition of the device under test in the prediction stage; Based on the current state parameter, the historical state parameter, the state parameter difference, the influence value and the time constant, the current state parameter of the unknown point of the device under test is predicted.
2. The parameter prediction method according to claim 1, wherein: In the prediction stage, current state parameters and historical state parameters of known points of the device under test are obtained through measurement, including: In the prediction stage, the state parameters of the known points are measured based on preset time intervals to obtain the current state parameters measured at the current moment and the historical state parameters measured at at least one historical moment.
3. The parameter prediction method according to claim 1, wherein: The state parameter difference is determined in the following manner: During the calibration phase, the state parameters of known points of the device under test are monitored; In a case where the state parameter of the known point remains unchanged within a preset monitoring time, the state parameter difference is calculated based on the state parameter of the known point and the state parameter of the unknown point.
4. The parameter prediction method according to claim 1, wherein: The time constant is determined as follows: During the calibration phase, the difference between the state parameters of the known points of the device under test and the state parameters of the unknown points is monitored; Drawing a difference time curve according to the relationship between the difference and time; performing exponential fitting on the difference time curve; The time constant is determined according to the fitting result.
5. The parameter prediction method according to claim 1, wherein: Determining the influence value of the preset influence factor on the state parameter includes: Obtaining the maximum impact value of each influencing factor on the state parameter; Get the weight of each impact factor; The influence value is calculated according to the maximum influence value and the weight.
6. The parameter prediction method according to claim 1, wherein: The predicting the current state parameter of the unknown point of the device under test based on the current state parameter, the historical state parameter, the state parameter difference, the influence value and the time constant includes: Calculating a correction factor based on the current state parameter and the historical state parameter, wherein the correction factor is used to express the degree of influence of the change of the state parameter of the known point on the state parameter difference; Based on the current state parameter, the correction factor, the state parameter difference, the influence value, the time constant and a preset state parameter prediction formula, the current state parameter of the unknown point of the device under test is calculated.
7. The parameter prediction method according to any one of claims 1 to 6, characterized in that: The state parameters include: temperature or air pressure.
8. A parameter prediction device, characterized in that: include: A measurement module, configured to obtain, during the prediction phase, current state parameters and historical state parameters of a known point of the device under test by measurement, wherein the number of the historical state parameters is at least one; A first acquisition module is used to obtain a state parameter difference between the known point and the unknown point of the device under test in a steady state; A second acquisition module is used to obtain a time constant of the device under test for a state parameter; A first determining module is configured to determine an influence value of a preset influencing factor on the state parameter, wherein the preset influencing factor is determined based on the state parameter and the operating condition of the device under test in the prediction stage; A prediction module is used to predict the current state parameter of the unknown point of the device under test based on the current state parameter, the historical state parameter, the state parameter difference, the influence value and the time constant.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.
10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by one or more processors, the method according to any one of claims 1 to 7 is implemented.