A spacecraft failure prediction processing method and device

Abstract

The application provides a spacecraft fault prediction processing method and device, and relates to the technical field of measurement and control. The method comprises the following steps: acquiring a single telemetry parameter of spacecraft fault prediction, determining a risk state of the single telemetry parameter according to a preset numerical interval in which a parameter value of the single telemetry parameter is located and the parameter value; if it is determined that the risk state reaches a preset level risk state, acquiring a historical time sequence parameter value of the single telemetry parameter; and predicting parameter value overrun according to the historical time sequence parameter value. The device executes the above method. The spacecraft fault prediction processing method and device provided in the embodiment of the application can improve the real-time performance and ease of use of spacecraft fault prediction.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of measurement and control, in particular to a spacecraft fault prediction processing method and device. BACKGROUND

[0002] With the continuous advancement of space engineering technology, the density of space missions is increasing, the flight measurement and control task is becoming more and more complex, and the probability of spacecraft failure is rapidly increasing. In order to ensure that the measurement and control system can quickly judge and accurately control the operation state of the spacecraft, high requirements are put forward for the real-time performance and ease of use of the spacecraft fault prediction.

[0003] The prior art usually uses an expert system and a machine learning system to complete fault prediction, and the real-time performance and ease of use of fault prediction need to be improved. SUMMARY

[0004] In view of the problems in the prior art, the embodiments of the present application provide a spacecraft fault prediction processing method and device, which can at least partially solve the problems in the prior art.

[0005] In one aspect, the present application provides a spacecraft fault prediction processing method, comprising:

[0006] Obtaining a single telemetry parameter for spacecraft fault prediction, determining a risk state of the single telemetry parameter according to a preset numerical interval in which a parameter value of the single telemetry parameter is located and the parameter value;

[0007] If it is determined that the risk state reaches a preset level risk state, obtaining a historical time sequence parameter value of the single telemetry parameter;

[0008] Predicting the parameter value out-of-limit according to the historical time sequence parameter value.

[0009] The prediction of the parameter value out-of-limit according to the historical time sequence parameter value comprises:

[0010] Decomposing the historical time sequence parameter value to obtain time sequence data components and parameter value data components;

[0011] Calculating the average value of each time sequence data component to obtain a first average value vector, and calculating the average value of each parameter value data component to obtain a second average value vector;

[0012] According to the first average value vector, the second average value vector and each historical time sequence parameter value, a fitting value vector is calculated;

[0013] The vector similarity between the fitting value vector and the second average value vector is calculated, and the vector similarity calculation result is taken as a probability value of the predictable parameter value out-of-limit.

[0014] wherein the calculating a predicted value vector according to the first average value vector, the second average value vector and each historical time series parameter value comprises:

[0015] An intermediate variable k is calculated according to the following formula:

[0016] k = ∑(xi-x)(yi-y) / (∑(xi-x) 2 )

[0017] wherein x is the first average value vector, y is the second average value vector, xi is a time series data component of the i-th historical time series parameter value, and yi is a parameter value data component of the i-th historical time series parameter value;

[0018] An intermediate variable d is calculated according to the following formula:

[0019] d = y-kx

[0020] The predicted value vector ypredict is calculated according to the following formula:

[0021] ypredict = kxi+d.

[0022] wherein the spacecraft fault prediction processing method further comprises:

[0023] calculating an overrun time of the parameter value according to the preset numerical interval and the historical time series parameter value.

[0024] wherein the calculating an overrun time of the parameter value according to the preset numerical interval and the historical time series parameter value comprises:

[0025] if it is determined that k is greater than zero and a maximum endpoint value b of the preset numerical interval is greater than d, the overrun time t0 is calculated according to the following formula:

[0026] t0 = (b-d) / k.

[0027] wherein the calculating an overrun time of the parameter value according to the preset numerical interval and the historical time series parameter value comprises:

[0028] if it is determined that k is less than zero and a minimum endpoint value a of the preset numerical interval is less than d, the overrun time t0 is calculated according to the following formula:

[0029] t0 = (a-d) / k.

[0030] wherein the spacecraft fault prediction processing method comprises:

[0031] acquire multiple telemetry parameters of a spacecraft fault prediction; a relationship between the multiple telemetry parameters and a spacecraft fault is represented by a spacecraft fault rule based on a time sequence logic;

[0032] perform a classification calculation on the spacecraft fault rule based on a state transition sequence, and determine a risk state of the multiple telemetry parameters according to a classification calculation result;

[0033] if it is determined that the risk state reaches a preset level risk state, perform a calculation on a formula logic relationship of the spacecraft fault rule based on the state transition sequence;

[0034] calculate an overrun time of the multiple telemetry parameters according to a formula logic relationship calculation result and a spacecraft on-board time corresponding to each spacecraft fault state.

[0035] The classification calculation on the spacecraft fault rule based on the state transition sequence comprises:

[0036] perform a classification calculation on the spacecraft fault rule based on the state transition sequence according to a preset classification logic calculation rule;

[0037] The preset classification logic calculation rule comprises a preset classification logic calculation mode corresponding to each preset formula expression mode.

[0038] The calculation on the formula logic relationship of the spacecraft fault rule based on the state transition sequence comprises:

[0039] perform a classification calculation on the first three data of the state transition sequence and the formula logic relationship based on the state transition sequence to obtain a formula logic relationship calculation result.

[0040] The calculation of the overrun time of the telemetry parameters according to the formula logic relationship calculation result and the spacecraft on-board time corresponding to each spacecraft fault state comprises:

[0041] if a first spacecraft on-board time corresponding to a spacecraft fault state corresponding to second data of the state transition sequence is less than a second spacecraft on-board time corresponding to a spacecraft fault state corresponding to third data of the state transition sequence, calculate the overrun time according to the formula logic relationship calculation result, the first spacecraft on-board time and the second spacecraft on-board time.

[0042] The calculation of the overrun time according to the formula logic relationship calculation result, the first spacecraft on-board time and the second spacecraft on-board time comprises:

[0043] an intermediate variable V is calculated according to the following formula:

[0044] V=(f0-f1) / (s0.time-s1.time)

[0045] Wherein, s0.time is the first spacecraft on-board time corresponding to the spacecraft failure state corresponding to the second item of data, s1.time is the second spacecraft on-board time corresponding to the spacecraft failure state corresponding to the third item of data, f0 is the formula logic relationship calculation result corresponding to the first item of data of the state transition sequence in the formula logic relationship calculation result, f1 is the formula logic relationship calculation result corresponding to the second item of data of the state transition sequence in the formula logic relationship calculation result;

[0046] If it is determined that V is greater than zero, the over-limit time is calculated according to the following formula:

[0047] t0=(100-f0) / V.

[0048] Wherein, the spacecraft failure prediction processing method further comprises:

[0049] If it is determined that V is less than or equal to zero, an error message is generated.

[0050] Wherein, the spacecraft failure prediction processing method further comprises:

[0051] If the first spacecraft on-board time corresponding to the spacecraft failure state corresponding to the second item of data of the state transition sequence is greater than or equal to the second spacecraft on-board time corresponding to the spacecraft failure state corresponding to the third item of data of the state transition sequence, an error message is generated.

[0052] In one aspect, the present application provides a spacecraft failure prediction processing device, comprising:

[0053] A determination unit is configured to obtain a single telemetry parameter of spacecraft failure prediction, and determine a risk state of the single telemetry parameter according to a preset numerical interval in which a parameter value of the single telemetry parameter is located and the parameter value.

[0054] A obtaining unit is configured to obtain a historical time sequence parameter value of the single telemetry parameter if it is determined that the risk state reaches a preset level risk state.

[0055] A prediction unit is configured to predict over-limit of the parameter value according to the historical time sequence parameter value.

[0056] In another aspect, the present application provides a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to realize the following method:

[0057] The single telemetry parameter for spacecraft fault prediction is acquired, and a risk state of the single telemetry parameter is determined according to a preset numerical interval in which a parameter value of the single telemetry parameter is located and the parameter value.

[0058] If it is determined that the risk state reaches a preset level risk state, a historical time sequence parameter value of the single telemetry parameter is acquired.

[0059] The parameter value overrun is predicted according to the historical time sequence parameter value.

[0060] The embodiment of the application provides a computer readable storage medium, comprising:

[0061] The computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the following method:

[0062] The single telemetry parameter for spacecraft fault prediction is acquired, and a risk state of the single telemetry parameter is determined according to a preset numerical interval in which a parameter value of the single telemetry parameter is located and the parameter value.

[0063] If it is determined that the risk state reaches a preset level risk state, a historical time sequence parameter value of the single telemetry parameter is acquired.

[0064] The parameter value overrun is predicted according to the historical time sequence parameter value.

[0065] The embodiment of the application further provides a computer program product, comprising a computer program, and the computer program is executed by a processor to implement the following method:

[0066] The single telemetry parameter for spacecraft fault prediction is acquired, and a risk state of the single telemetry parameter is determined according to a preset numerical interval in which a parameter value of the single telemetry parameter is located and the parameter value.

[0067] If it is determined that the risk state reaches a preset level risk state, a historical time sequence parameter value of the single telemetry parameter is acquired.

[0068] The parameter value overrun is predicted according to the historical time sequence parameter value.

[0069] The spacecraft fault prediction processing method and device provided by the embodiment of the application can acquire a single telemetry parameter for spacecraft fault prediction, determine a risk state of the single telemetry parameter according to a preset numerical interval in which a parameter value of the single telemetry parameter is located and the parameter value, acquire a historical time sequence parameter value of the single telemetry parameter if it is determined that the risk state reaches a preset level risk state, and predict the parameter value overrun according to the historical time sequence parameter value, so that the real-time performance and the ease of use of spacecraft fault prediction can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0070] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor. In the drawings:

[0071] Figure 1 is a flowchart of a spacecraft fault prediction processing method provided by an embodiment of the present application.

[0072] Figure 2 is a flowchart of a spacecraft fault prediction processing method provided by another embodiment of the present application.

[0073] Figure 3 is a structural diagram of a spacecraft fault prediction processing device provided by an embodiment of the present application.

[0074] Figure 4 is a structural diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0075] In order to make the purpose, technical solutions and advantages of the embodiments of the present application more clear, the following will further describe the embodiments of the present application in combination with the drawings. Herein, the illustrative embodiments of the present application and their descriptions are used to explain the present application, but not as a limitation of the present application. It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other at will.

[0076] Figure 1 is a flowchart of a spacecraft fault prediction processing method provided by an embodiment of the present application, as shown in Figure 1 The spacecraft fault prediction processing method provided by the embodiments of the present application comprises:

[0077] Step S1: acquiring a single telemetry parameter of spacecraft fault prediction, and determining a risk state of the single telemetry parameter according to a preset numerical interval in which a parameter value of the single telemetry parameter is located and the parameter value.

[0078] Step S2: if it is determined that the risk state reaches a preset level risk state, acquiring a historical time sequence parameter value of the single telemetry parameter.

[0079] Step S3: predicting the parameter value out of limit according to the historical time sequence parameter value.

[0080] In step S1, the device obtains a single telemetry parameter of a spacecraft fault prediction, and determines a risk state of the single telemetry parameter according to a preset numerical interval in which a parameter value of the single telemetry parameter is located and the parameter value. The device can be a computer device or the like that executes the method, for example, a server. In the technical solution of the present application, the acquisition, storage, use, processing and the like of data comply with relevant provisions of national laws and regulations. For example Figure 2 The single-parameter overrun early warning is explained as follows:

[0081] The spacecraft parameter has a certain legal range, and exceeding the range is an abnormal state. The range is represented as follows:

[0082] (1) (v1, v2): v1 < parameter < v2

[0083] (2) (v1, ): v1 < parameter

[0084] (3) (, v2): parameter < v2

[0085] (4) [v1, v2): v1 <= parameter < v2

[0086] (5) (v1, v2]: v1 < parameter <= v2

[0087] (6) [v1, v2]: v1 <= parameter <= v2

[0088] (7) [v1, ): v1 <= parameter

[0089] (8) (, v2]: parameter <= v2

[0090] Multiple legal ranges are separated by “;”. When the system loads the parameter legal range, the overlapping intervals are merged, so that each parameter has a sequence of intervals that do not intersect each other to form its legal range. When the parameter value is in the legal interval, the closer to the boundary, the more likely to have an overrun anomaly. The present application designs a parameter danger degree index for each limited range parameter that slides to the anomaly.

[0091] When the value v of the parameter A is in the limited range, that is, v∈[a, b] or (a, b) or [a, b) or (a, b], the parameter danger degree function f is defined as follows:

[0092] f(v) = |(2v-a-b) / (b-a)|x100%

[0093] When f(v) <= 60%, the parameter is in a safe state; when 60% < f(v) <= 80%, the parameter is in a low-risk state; and when f(v) > 80%, the parameter is in a high-risk state. The state can be displayed together with the parameter to provide an intuitive display of the current state for the operator.

[0094] In step S2, the device obtains the historical time series parameter values of the single telemetry parameter if it determines that the risk state reaches the preset level risk state. For the parameters (80% < f(v) < 100%) of the high risk state (corresponding to the preset level risk state), the application designs an algorithm predict to predict the time of reaching the abnormal boundary. The historical time series parameter values of the single telemetry parameter can be expressed as follows:

[0095] < x1, y1 >,..., < xm, ym >.

[0096] In step S3, the device predicts the parameter value overrun according to the historical time series parameter values. The prediction of the parameter value overrun according to the historical time series parameter values includes:

[0097] Decompose the historical time series parameter values to obtain time series data components (x1...xm) and parameter value data components (y1...ym).

[0098] Calculate the average value of each time series data component to obtain a first average value vector x = (x1+...+xm) / m, and calculate the average value of each parameter value data component to obtain a second average value vector y = (y1+...+ym) / m.

[0099] According to the first average value vector, the second average value vector, and each historical time series parameter value, calculate a fitting value vector. The calculation of the fitting value vector according to the first average value vector, the second average value vector, and each historical time series parameter value includes:

[0100] Calculate an intermediate variable k according to the following formula:

[0101] k = ∑(xi-x)(yi-y) / (∑(xi-x) 2 )

[0102] where x is the first average value vector, y is the second average value vector, xi is the time series data component of the i-th historical time series parameter value, and yi is the parameter value data component of the i-th historical time series parameter value.

[0103] Calculate an intermediate variable d according to the following formula:

[0104] d = y-k×x

[0105] Calculate the fitting value vector ypredict according to the following formula:

[0106] ypredict = k×xi+d.

[0107] calculating a vector similarity between the fitting value vector and the second average value vector, and taking the vector similarity calculation result as a probability value of the predictable parameter value overrunning. The vector similarity between the fitting value vector and the second average value vector can be calculated using a Pearson algorithm.

[0108] The spacecraft fault prediction processing method further comprises:

[0109] calculating an overrunning time of the parameter value according to the preset numerical interval and the historical time sequence parameter value.

[0110] The calculating of the overrunning time of the parameter value according to the preset numerical interval and the historical time sequence parameter value comprises:

[0111] if it is determined that k is greater than zero and a maximum endpoint value b of the preset numerical interval is greater than d, the overrunning time t0 is calculated according to the following formula:

[0112] t0=(b-d) / k.

[0113] The calculating of the overrunning time of the parameter value according to the preset numerical interval and the historical time sequence parameter value comprises:

[0114] if it is determined that k is less than zero and a minimum endpoint value a of the preset numerical interval is less than d, the overrunning time t0 is calculated according to the following formula:

[0115] t0=(a-d) / k.

[0116] Specifically, the following is described:

[0117] Algorithm name: predict

[0118] Input: historical value sequence <x1, y1>,..., <xm, ym>.

[0119] Output: t0--parameter overrunning time, p--confidence probability.

[0120] Return value: true--there is an overrunning time t0, false--the overrunning time t0 is not assigned.

[0121] Process:

[0122] 1. Let x=(x1+...+xm) / m, y=(y1+...+ym) / m, then k=∑(xi-x)(yi-y) / (∑(xi-x) 2 ), d=y-k*x.

[0123] 2. Calculate ypredict=k×xi+d, i=1,..., m.

[0124] 3. Calculate the similarity p between the fitted value vector ypredict and the measured value vector y

[0125] 4. If k > 0, then

[0126] (1) If b > d, calculate t0 = (b - d) / k and return true.

[0127] 5. If k < 0, then

[0128] (1) If a < d, calculate t0 = (a - d) / k and return true.

[0129] 6. Return false.

[0130] In the first step, the nearest m historical values <x1, y1>,..., <xm, ym> of the parameter are used to fit the parameter change curve f(t) = k × t + d by the least squares method, where t is the time. In the second to third steps, the Pearson algorithm is used to calculate the similarity between the fitted value vector and the measured value vector as the confidence of the result. In the fourth to fifth steps, the method of function extrapolation is applied to calculate the time when the curve reaches the boundary of the legal range, so as to master the time when an anomaly may occur in advance.

[0131] As Figure 2 shown, the multi-parameter over-limit warning is explained as follows:

[0132] Obtain the multi-telemetry parameters for spacecraft fault prediction; the relationship between the multi-telemetry parameters and spacecraft faults is represented by the spacecraft fault rules based on temporal logic; the specific description is as follows:

[0133] The fault judgment conditions of the spacecraft fault plan usually have the following categories:

[0134] 1. Parameter anomaly: p > v, p < v, p = v, p!= v, v1 <= p <= v2, Multiple conditions can be combined by "AND" and "OR", where p is the parameter and v is the value.

[0135] 2. Parameter combination anomaly: exp > 0. Where exp is a numerical expression composed of several parameters, values and functions.

[0136] 3. Anomaly of a certain (few) bits of the parameter: ParaCode_D1 = 1, ParaCode_D1~D5 = 6.

[0137] 4. The parameter continuously increases / decreases / remains unchanged.

[0138] 5. A certain condition has ever / always been true within n seconds.

[0139] 6. A condition has been / always been true in the last n frames for a parameter.

[0140] 7. A condition is true n seconds after an instruction is issued.

[0141] Each type of fault can be achieved by combining the above cases, and the fault rules can be written in the form of logical expressions. In addition to the four arithmetic operations and logical operations, special judgment and function calculation are defined by predicates and function words.

[0142] The fault rules based on temporal logic are composed of predicates / propositions, function words, constants, variables, logical relationship symbols and temporal operators. Let D be the domain, then n-ary predicate P: D*D*...*D-->bool, usually represented by capital letters P, Q. Proposition is a 0-ary predicate. n-ary function f: D*D*...*D-->D, usually represented by lowercase letters f, g, h. Constants are represented by a, b, c, and variables are represented by x, y, z.[t], <t>{n,m} is a temporal operator, the set of temporal operators is denoted as TOP. t>=0 means t time in the past (history) from the current time.

[0143] [t]P: P has been true for t time before the current time.

[0144] <t>P: P has been true in the last t time before the current time.

[0145] {n,m}P: P has been true in the last n frames for m frames before the current time.

[0146] Definition (Term) Let D be the domain of discourse, the definition of term is as follows:

[0147] (i) If x is a variable, then x is a term.

[0148] (ii) If a is a constant, then a is a term.

[0149] (iii) If t is a term, then (t) is a term.

[0150] (iv) If f: D1* D2*... * Dn--> D is an n-ary function, and t1, t2,..., tn are terms, then f(t1, t2,..., tn) is a term.

[0151] (v) A term can only be constructed by using (i)~(iv) for a finite number of times.

[0152] The set of terms is denoted as Term.

[0153] The definition of logical formula is as follows:

[0154] (1) If P is an n-ary predicate, and t1,..., tn∈ Term, then P(t1,..., tn) is a formula.

[0155] (2) If P and Q are formulas, and op∈ TOP, then (P), PVQ, P / \Q, ~P, op P is a formula.

[0156] (3) A formula can only be constructed by using (1) and (2) for a finite number of steps.

[0157] The fault is defined by the predicate Fault(s, i), which indicates that the fault is of level i and the fault name is s.

[0158] Rule definition: A logical rule R is a logical expression of the form P-->Q, where P and Q are formulas.

[0159] In order to describe the state of terms / formulas at different times, Kripke semantics is used to calculate the truth value of time transient, and each time instant is a possible world (i.e. state), and a transition from one time instant to the next time instant.

[0160] The semantics of formulas is explained by the Kripke structure <S, I, R, Lable>, where S is the set of states, is the initial state set, is a transition relation, Label: S-->2AP is a state labeling function.

[0161] Label defines predicates / propositions that are true for each state (instantaneous world), let the sequence of state transitions be sigma = s0s1...sm = sigma0 = s0sigma1, 0 <= t <= m, si is a state. If A is a formula, Asi denotes the truth value of A in si, Asi is true if A is in Label(si), otherwise false.

[0162] The spacecraft fault rule is classified and calculated based on the state transition sequence, and the risk state of the multiple telemetry parameters is determined according to the classification calculation result; the classification calculation of the spacecraft fault rule based on the state transition sequence comprises:

[0163] According to the preset classification logic calculation rule, the spacecraft fault rule is classified and calculated based on the state transition sequence;

[0164] The preset classification logic calculation rule comprises a preset classification logic calculation mode corresponding to each preset formula expression mode.

[0165] The following is explained:

[0166] Algorithm name: f

[0167] Input: state transition sequence sigma, formula P

[0168] Return: danger degree [0, 100]

[0169] Process:

[0170] 1. Classification calculation is as follows:

[0171] If P = True, then f(P) sigma = 100.

[0172] If P = False, then f(P) sigma = 0.

[0173] If P = ~C, then f(P) sigma = 100-f(C) sigma.

[0174] If P = B / \C, then f(P) sigma = f(B / \C) sigma = (f(B) sigma + f(C) sigma) / 2.

[0175] If P = BVC, then f(P) sigma = f(BVC) sigma = max{f(B) sigma, f(C) sigma}.

[0176] If P = [t]B, then f(P)σ = 100 if σ(P) = True for t > 0, otherwise there exists i (0 <= i < t) such that σi(B) = False, so f(P)σ = min{i | f(B)σi = False, 0 <= i < t} x 100 / t.

[0177] f(P)σ = f(B)σ for t = 0.

[0178] If P = [t]B, <t>B, then f(P)σ = max{f(B)σi | 0 <= i < t}.

[0179] If P = {n, m} B, where 0 < m < n, then f(P)σ = min{m, #{f(B)σi | 0 <= i <= n-1}} x 100 / m.

[0180] 2. Return the calculation result of f(P)σ.

[0181] If it is determined that the risk state reaches a preset level risk state, then the formula logic relationship of the spacecraft failure rule based on the state transition sequence is calculated;

[0182] The risk degree f(P→Q)σ of the rule P→Q is f(P)σ.

[0183] For the rule of high risk state (80% < f(P→Q)σ < 100%), the formula logic relationship of the spacecraft failure rule based on the state transition sequence is calculated, and subsequent steps are performed.

[0184] The calculation of the formula logic relationship of the spacecraft failure rule based on the state transition sequence includes:

[0185] The first three data of the state transition sequence and the formula logic relationship are calculated based on the state transition sequence to obtain a formula logic relationship calculation result. If the state transition sequence is σ = σ0 = s0σ1 = s0s1σ2, the first three data of the state transition sequence are σ0, s0σ1, and s0s1σ2, respectively.

[0186] The formula logic relationship is the calculation result of f(P)σ, and the formula logic relationship calculation result is f0 = f(P)σ0 and f1 = f(P)σ1.

[0187] According to the formula logic relationship calculation result and the spacecraft on-orbit time corresponding to each spacecraft failure state, the overrun time of the multiple telemetry parameters is calculated. According to the formula logic relationship calculation result and the spacecraft on-orbit time corresponding to each spacecraft failure state, the overrun time of the telemetry parameter is calculated, including:

[0188] If the first spacecraft on-board time (corresponding to s0.time) corresponding to the spacecraft fault state (corresponding to s0) corresponding to the second item of data (corresponding to s0σ1) of the state transition sequence is less than the second spacecraft on-board time (corresponding to s1.time) corresponding to the spacecraft fault state (corresponding to s1) corresponding to the third item of data (corresponding to s0s1σ2) of the state transition sequence, the over-limit time is calculated according to the formula logic relationship calculation result, the first spacecraft on-board time and the second spacecraft on-board time. The calculation of the over-limit time according to the formula logic relationship calculation result, the first spacecraft on-board time and the second spacecraft on-board time comprises:

[0189] An intermediate variable V is calculated according to the following formula:

[0190] V=(f0-f1) / (s0.time-s1.time)

[0191] Wherein, s0.time is the first spacecraft on-board time corresponding to the spacecraft fault state corresponding to the second item of data, s1.time is the second spacecraft on-board time corresponding to the spacecraft fault state corresponding to the third item of data, f0 is the formula logic relationship calculation result corresponding to the first item of data (corresponding to σ0) of the state transition sequence in the formula logic relationship calculation result, and f1 is the formula logic relationship calculation result corresponding to the second item of data (corresponding to s0σ1) of the state transition sequence in the formula logic relationship calculation result.

[0192] If it is determined that V is greater than zero, the over-limit time is calculated according to the following formula:

[0193] t0=(100-f0) / V.

[0194] The spacecraft fault prediction processing method further comprises:

[0195] If it is determined that V is less than zero, an error information is generated.

[0196] The spacecraft fault prediction processing method further comprises:

[0197] If the first spacecraft on-board time corresponding to the spacecraft fault state corresponding to the second item of data of the state transition sequence is greater than or equal to the second spacecraft on-board time corresponding to the spacecraft fault state corresponding to the third item of data of the state transition sequence, an error information is generated.

[0198] The following describes the prediction of the time of its arrival at an anomaly using the following algorithm predictRule:

[0199] Algorithm name: predictRule

[0200] Input: state transition sequence sigma = sigma0 = s0 sigma1 = s0 s1 sigma2, formula P.

[0201] Output: t0 - the abnormal time.

[0202] Return value: true - there is an overrunning time t0, false - the overrunning time t0 is not assigned.

[0203] Process:

[0204] 1. Calculate f0 = f(P) sigma0 and f1 = f(P) sigma1.

[0205] 2. If s0.time < s1.time,

[0206] 3. Then

[0207] 3.1 Calculate v = (f0 - f1) / (s0.time - s1.time), where si.time is the spacecraft on-board time when the si state is taken, i = 0, 1;

[0208] 3.2 If v > 0, then t0 = (100 - f0) / v.

[0209] 3.3 Return true.

[0210] 3.4 Otherwise, return false.

[0211] 4. Otherwise, return false.

[0212] The application proposes a real-time early warning method for single-parameter overrunning fault of a spacecraft, divides a parameter normal range into three intervals, predicts parameter overrunning time when the parameter value enters a high-risk interval, and uses the similarity of a fitting value of the parameter and a measured value as the credibility of early warning, so that single-parameter fault early warning is realized.

[0213] The application proposes a spacecraft fault rule danger degree calculation algorithm containing time sequence, solves the quantitative multi-parameter association relationship, i.e., the quantitative difficulty of abnormality, normalizes the calculation process of time sequence rule proximity to abnormality in a recursive definition manner, and solves the difficulty of logic rule early warning.

[0214] The spacecraft fault prediction processing method provided by the application embodiment acquires a single telemetry parameter of spacecraft fault prediction, determines a risk state of the single telemetry parameter according to a preset numerical interval in which a parameter value of the single telemetry parameter is located and the parameter value, acquires a historical time sequence parameter value of the single telemetry parameter if it is determined that the risk state reaches a preset level risk state, and predicts overrunning of the parameter value according to the historical time sequence parameter value, so that the real-time performance and the ease of use of spacecraft fault prediction can be improved.

[0215] Further, the predicting the parameter value overrun according to the historical time series parameter values comprises:

[0216] Decomposing the historical time series parameter values to obtain time series data components and parameter value data components; refer to the above description.

[0217] Calculating the average value of each time series data component to obtain a first average value vector, and calculating the average value of each parameter value data component to obtain a second average value vector; refer to the above description.

[0218] Calculating a fitting value vector according to the first average value vector, the second average value vector and each historical time series parameter value; refer to the above description.

[0219] Calculating the vector similarity between the fitting value vector and the second average value vector, and taking the vector similarity calculation result as the probability value of the predictable parameter value overrun; refer to the above description.

[0220] Further, the calculating a fitting value vector according to the first average value vector, the second average value vector and each historical time series parameter value comprises:

[0221] Calculating an intermediate variable k according to the following formula:

[0222] k = ∑(xi-x)(yi-y) / (∑(xi-x) 2 )

[0223] Wherein, x is the first average value vector, y is the second average value vector, xi is the time series data component of the i-th historical time series parameter value, and yi is the parameter value data component of the i-th historical time series parameter value; refer to the above description.

[0224] Calculating an intermediate variable d according to the following formula:

[0225] d = y-k×x

[0226] Calculating the fitting value vector ypredict according to the following formula:

[0227] ypredict = k×xi+d; refer to the above description.

[0228] Further, the spacecraft fault prediction processing method further comprises:

[0229] Calculating the overrun time of the parameter value according to the preset numerical interval and the historical time series parameter value; refer to the above description.

[0230] Further, the calculation of the overrun time of the parameter value according to the preset numerical interval and the historical time series parameter value comprises:

[0231] If it is determined that k is greater than zero and the maximum endpoint value b of the preset numerical interval is greater than d, the overrun time t0 is calculated according to the following formula:

[0232] t0=(b-d) / k. Refer to the above description for details.

[0233] Further, the calculation of the overrun time of the parameter value according to the preset numerical interval and the historical time series parameter value comprises:

[0234] If it is determined that k is less than zero and the minimum endpoint value a of the preset numerical interval is less than d, the overrun time t0 is calculated according to the following formula:

[0235] t0=(a-d) / k. Refer to the above description for details.

[0236] Further, the spacecraft fault prediction processing method comprises:

[0237] Obtaining multiple telemetry parameters for spacecraft fault prediction; the relationship between the multiple telemetry parameters and the spacecraft fault is represented by a spacecraft fault rule based on time sequence logic; refer to the above description for details.

[0238] Performing classification calculation on the spacecraft fault rule based on a state transition sequence, and determining the risk state of the multiple telemetry parameters according to the classification calculation result; refer to the above description for details.

[0239] If it is determined that the risk state reaches a preset level risk state, the formula logic relationship of the spacecraft fault rule based on the state transition sequence is calculated; refer to the above description for details.

[0240] According to the formula logic relationship calculation result and the spacecraft on-time corresponding to each spacecraft fault state, the overrun time of the multiple telemetry parameters is calculated. Refer to the above description for details.

[0241] Further, the classification calculation on the spacecraft fault rule based on the state transition sequence comprises:

[0242] According to a preset classification logic calculation rule, the classification calculation on the spacecraft fault rule based on the state transition sequence is performed; refer to the above description for details.

[0243] The preset classification logic calculation rule comprises a preset classification logic calculation mode corresponding to each preset formula expression mode. Refer to the above description for details.

[0244] Further, the calculating the formula logic relation of the spacecraft fault rule based on the state transition sequence comprises:

[0245] The state transition sequence-based classification calculation is performed on the first three data of the state transition sequence and the formula logic relation to obtain a formula logic relation calculation result. Refer to the above description for details.

[0246] Further, the calculating the overrun time of the telemetry parameter according to the formula logic relation calculation result and the spacecraft on-board time corresponding to each spacecraft fault state comprises:

[0247] If the first spacecraft on-board time corresponding to the spacecraft fault state corresponding to the second data of the state transition sequence is less than the second spacecraft on-board time corresponding to the spacecraft fault state corresponding to the third data of the state transition sequence, the overrun time is calculated according to the formula logic relation calculation result, the first spacecraft on-board time and the second spacecraft on-board time. Refer to the above description for details.

[0248] Further, the calculating the overrun time according to the formula logic relation calculation result, the first spacecraft on-board time and the second spacecraft on-board time comprises:

[0249] An intermediate variable V is calculated according to the following formula:

[0250] V=(f0-f1) / (s0.time-s1.time)

[0251] Wherein, s0.time is the first spacecraft on-board time corresponding to the spacecraft fault state corresponding to the second data, s1.time is the second spacecraft on-board time corresponding to the spacecraft fault state corresponding to the third data, f0 is the formula logic relation calculation result corresponding to the first data of the state transition sequence in the formula logic relation calculation result, and f1 is the formula logic relation calculation result corresponding to the second data of the state transition sequence in the formula logic relation calculation result.

[0252] If it is determined that V is greater than zero, the overrun time is calculated according to the following formula:

[0253] t0=(100-f0) / V. Refer to the above description for details.

[0254] Further, the spacecraft fault prediction processing method further comprises:

[0255] If it is determined that V is less than or equal to zero, an error message is generated. Refer to the above description for details.

[0256] Further, the spacecraft fault prediction processing method further comprises:

[0257] If the first spacecraft on-board time corresponding to the spacecraft fault state corresponding to the second item of data of the state transition sequence is greater than or equal to the second spacecraft on-board time corresponding to the spacecraft fault state corresponding to the third item of data of the state transition sequence, error information is generated. Referring to the above description, no further description is given.

[0258] Figure 3 is a structural schematic diagram of a spacecraft fault prediction processing device provided by an embodiment of the present application, as Figure 3 indicated, the spacecraft fault prediction processing device provided by the embodiment of the present application comprises a determination unit 301, an acquisition unit 302 and a prediction unit 303, wherein:

[0259] The determination unit 301 is configured to acquire a single telemetry parameter for spacecraft fault prediction, determine a risk state of the single telemetry parameter according to a preset numerical interval in which a parameter value of the single telemetry parameter is located and the parameter value, the acquisition unit 302 is configured to acquire a historical time sequence parameter value of the single telemetry parameter if the determined risk state reaches a preset level risk state, and the prediction unit 303 is configured to predict that the parameter value is out of limit according to the historical time sequence parameter value.

[0260] Specifically, the determination unit 301 in the device is configured to acquire a single telemetry parameter for spacecraft fault prediction, determine a risk state of the single telemetry parameter according to a preset numerical interval in which a parameter value of the single telemetry parameter is located and the parameter value, the acquisition unit 302 is configured to acquire a historical time sequence parameter value of the single telemetry parameter if the determined risk state reaches a preset level risk state, and the prediction unit 303 is configured to predict that the parameter value is out of limit according to the historical time sequence parameter value.

[0261] The spacecraft fault prediction processing device provided by the embodiment of the present application acquires a single telemetry parameter for spacecraft fault prediction, determines a risk state of the single telemetry parameter according to a preset numerical interval in which a parameter value of the single telemetry parameter is located and the parameter value, acquires a historical time sequence parameter value of the single telemetry parameter if the determined risk state reaches a preset level risk state, and predicts that the parameter value is out of limit according to the historical time sequence parameter value, thereby improving the real-time performance and ease of use of spacecraft fault prediction.

[0262] The embodiment of the spacecraft fault prediction processing device provided by the embodiment of the present application can be specifically used to execute the processing procedures of the above-mentioned method embodiments, and the functions thereof will not be described here again, and the detailed description thereof can be referred to the above-mentioned method embodiments.

[0263] Figure 4 is a structural schematic diagram of a computer device provided by an embodiment of the present application, as Figure 4 As shown, the computer device comprises a memory 401, a processor 402 and a computer program stored on the memory 401 and capable of running on the processor 402, and the processor 402 implements the following method when executing the computer program:

[0264] obtaining a single telemetry parameter for spacecraft fault prediction, determining a risk state of the single telemetry parameter according to a preset numerical interval in which a parameter value of the single telemetry parameter is located and the parameter value;

[0265] if it is determined that the risk state reaches a preset hierarchical risk state, obtaining a historical time series parameter value of the single telemetry parameter;

[0266] predicting the parameter value out of limit according to the historical time series parameter value.

[0267] The embodiment discloses a computer program product, the computer program product comprises a computer program, and the computer program implements the following method when executed by a processor:

[0268] obtaining a single telemetry parameter for spacecraft fault prediction, determining a risk state of the single telemetry parameter according to a preset numerical interval in which a parameter value of the single telemetry parameter is located and the parameter value;

[0269] if it is determined that the risk state reaches a preset hierarchical risk state, obtaining a historical time series parameter value of the single telemetry parameter;

[0270] predicting the parameter value out of limit according to the historical time series parameter value.

[0271] The embodiment provides a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program implements the following method when executed by a processor:

[0272] obtaining a single telemetry parameter for spacecraft fault prediction, determining a risk state of the single telemetry parameter according to a preset numerical interval in which a parameter value of the single telemetry parameter is located and the parameter value;

[0273] if it is determined that the risk state reaches a preset hierarchical risk state, obtaining a historical time series parameter value of the single telemetry parameter;

[0274] predicting the parameter value out of limit according to the historical time series parameter value.

[0275] Compared with the technical solution in the prior art, the single telemetry parameter of the spacecraft fault prediction is acquired, the risk state of the single telemetry parameter is determined according to a preset numerical interval in which a parameter value of the single telemetry parameter is located and the parameter value, and if it is determined that the risk state reaches a preset level risk state, the historical time sequence parameter value of the single telemetry parameter is acquired; and the parameter value overrun is predicted according to the historical time sequence parameter value, so that the real-time performance and the ease of use of the spacecraft fault prediction can be improved.

[0276] Those skilled in the art will understand that embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0277] The present application is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce an apparatus that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for performing the functions specified in the flowchart

[0278] These computer program instructions can also be stored in a computer-readable memory that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including instruction means, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for performing the functions specified in the flowchart

[0279] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable data processing apparatus to produce a computer-implemented process, so that the instructions executed on the computer or other programmable data processing apparatus provide a process for implementing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for performing the functions specified in the flowchart

[0280] In the description of the present specification, the description of the terms "one embodiment", "one specific embodiment", "some embodiments", "for example", "exemplary", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in one or more embodiments or examples.

[0281] The specific embodiments described above further illustrate the objects, technical solutions and advantages of the present application. It should be understood that the above description is only for specific embodiments of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.< / t> < / t> < / t>

Claims

1. A spacecraft failure prediction processing method, characterized by, The method comprises the following steps: obtaining a single telemetry parameter for spacecraft failure prediction, determining a risk state of the single telemetry parameter according to a preset numerical interval in which a parameter value of the single telemetry parameter is located and the parameter value; if it is determined that the risk state reaches a preset level risk state, obtaining a historical time series parameter value of the single telemetry parameter; predicting that the parameter value is out of limit according to the historical time series parameter value; the step of predicting that the parameter value is out of limit according to the historical time series parameter value comprises: decomposing the historical time series parameter value to obtain time series data components and parameter value data components; calculating an average value of each time series data component to obtain a first average value vector, and calculating an average value of each parameter value data component to obtain a second average value vector; calculating a fitting value vector according to the first average value vector, the second average value vector and each historical time series parameter value; calculating a vector similarity between the fitting value vector and the second average value vector, and taking the vector similarity calculation result as a probability value of a predictable parameter value out of limit; the step of calculating a fitting value vector according to the first average value vector, the second average value vector and each historical time series parameter value comprises: calculating an intermediate variable k according to the following formula: k = ∑(xi-x)(yi-y) / (∑(xi-x) 2 ) wherein x is the first average value vector, y is the second average value vector, xi is a time series data component of the i th historical time series parameter value, and yi is a parameter value data component of the i th historical time series parameter value; calculating an intermediate variable d according to the following formula: d=y-k×x calculating the fitting value vector ypredict according to the following formula: ypredict=k×xi+d.

2. The spacecraft failure prediction processing method of claim 1, wherein, The method further comprises: calculating an out-of-limit time of the parameter value according to the preset numerical interval and the historical time series parameter value.

3. The spacecraft failure prediction processing method according to claim 2, characterized by, the step of calculating the out-of-limit time of the parameter value according to the preset numerical interval and the historical time series parameter value comprises: if it is determined that k is greater than zero and a maximum endpoint value b of the preset numerical interval is greater than d, the out-of-limit time t0 is calculated according to the following formula: t0=(b-d) / k.

4. The spacecraft failure prediction processing method according to claim 2, characterized by, the step of calculating the out-of-limit time of the parameter value according to the preset numerical interval and the historical time series parameter value comprises: if it is determined that k is less than zero and a minimum endpoint value a of the preset numerical interval is less than d, the out-of-limit time t0 is calculated according to the following formula: t0=(a-d) / k.

5. A spacecraft failure prediction processing apparatus characterized by comprising: The method comprises the following steps: a determination unit is configured to obtain a single telemetry parameter for spacecraft failure prediction, and determine a risk state of the single telemetry parameter according to a preset numerical interval in which a parameter value of the single telemetry parameter is located and the parameter value; an obtaining unit is configured to obtain a historical time series parameter value of the single telemetry parameter if it is determined that the risk state reaches a preset level risk state; a prediction unit is configured to predict that the parameter value is out of limit according to the historical time series parameter value; the prediction unit is specifically configured to: decompose the historical time series parameter value to obtain time series data components and parameter value data components; calculating an average value of each time series data component to obtain a first average value vector, and calculating an average value of each parameter value data component to obtain a second average value vector; calculating a fitting value vector according to the first average value vector, the second average value vector and each historical time series parameter value; calculating a vector similarity between the fitting value vector and the second average value vector, and taking the vector similarity as a probability value of the parameter value exceeding the limit; the calculating a fitting value vector according to the first average value vector, the second average value vector and each historical time series parameter value comprises: calculating an intermediate variable k according to the following formula: k = ∑(xi-x)(yi-y) / (∑(xi-x) 2 ) wherein x is the first average value vector, y is the second average value vector, xi is a time series data component of the i th historical time series parameter value, and yi is a parameter value data component of the i th historical time series parameter value; calculating an intermediate variable d according to the following formula: d = y - k × x calculating the fitting value vector y predict according to the following formula: y predict = k × xi + d.

6. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the method of any one of claims 1 to 4 when executing the computer program.

7. A computer readable storage medium characterized in that, The computer readable storage medium stores a computer program, and the computer program implements the method of any one of claims 1 to 4 when executed by the processor.

8. A computer program product, characterised in that, The computer program product comprises a computer program, and the computer program implements the method of any one of claims 1 to 4 when executed by the processor.

Images