A method and system for constructing a motor parameter monitoring model

Abstract

The present disclosure belongs to the field of motor monitoring and data processing technology, and in particular, relates to a method and system for constructing a motor parameter monitoring model. The method specifically includes: obtaining current motor drive parameters and drive parameter historical data during motor operation; classifying the current motor drive parameters based on the drive parameter historical data to obtain at least one classification data as basic data for constructing a motor drive parameter model; determining the parameter relationship between each classification data and the motor parameters; constructing a motor parameter fusion model based on the parameter relationship and the classification data; using the constructed motor parameter fusion model to determine and evaluate the motor parameters to obtain the motor parameters during motor operation. The motor drive parameter model constructed using the method and system disclosed in the present disclosure can quickly and accurately calculate and evaluate the motor parameters, obtain highly accurate motor parameters during operation, and improve the motor operation efficiency.

Description

Technical Field

[0001] The present invention belongs to the technical field of motor monitoring and data processing, and in particular, relates to a method and system for constructing a motor parameter monitoring model. Background Art

[0002] With the continuous development and increasing intelligence of power systems, motors, as core equipment of power systems, are crucial to the stability and reliability of the entire system. However, in the long-term operation, motors may have various faults. If these faults are not predicted and detected in a timely and effective manner, they will have an adverse effect on the operation of the power system and even cause accidents.

[0003] In the prior art, in the model-based motor parameter monitoring and evaluation, the model construction structure is simple and does not take into account the parameter changes and relationships in different scenarios, which makes the parameter results in the identification and analysis prone to deviations, leading to misjudgment of the motor status. Summary of the invention

[0004] The first aspect of the present disclosure aims to provide a method for constructing a motor parameter monitoring model in order to solve the above problem. The method specifically comprises the steps of:

[0005] Step 1, during the operation of the motor, obtaining current motor drive parameters and drive parameter history data;

[0006] Step 2: classify the current motor drive parameters based on the drive parameter history data to obtain at least one classification data as basic data for constructing a motor drive parameter model;

[0007] Step 3, determining a parameter relationship between each of the classification data and the motor parameters;

[0008] Step 4, constructing a motor parameter fusion model based on the parameter relationship and the classification data;

[0009] Step 5: Using the constructed motor parameter fusion model, the motor parameters are determined and evaluated to obtain the motor parameters during the motor operation process.

[0010] Optionally, the motor driving parameters are external parameters that drive or affect the operation of the motor, including at least one of power parameters, external environmental parameters and load parameters, wherein the power parameters include voltage and current; and the external environmental parameters include temperature and humidity.

[0011] Optionally, the step 2 specifically includes:

[0012] For each parameter of the current motor drive parameter, analyzing all drive parameter historical data corresponding to the parameter to obtain a change rule of the parameter;

[0013] The current motor drive parameters are classified according to the change rule of each parameter to obtain at least one classification data.

[0014] Optionally, the change rule includes at least one of the following situations:

[0015] Regular changes, each data in the parameter of the regular changes satisfies a relational expression corresponding to the parameter, and when the motor is in a non-fault state, the parameter is within a first expected parameter range;

[0016] Irregular changes, the irregularly changing parameters are irregular parameters, and the difference between at least two data in the regularly changing parameters is greater than the difference threshold;

[0017] No change, and the difference between each data in the unchanged parameter is not greater than the difference threshold.

[0018] Optionally, the parameter relationship includes at least one of the following situations:

[0019] The motor parameters are determined by the regularly changing parameters and the transformation sequence;

[0020] The motor parameters are determined by the irregularly changing parameters and probability matrix and parameter conversion formula;

[0021] The motor parameters are determined by the unchanged parameters and a proportionality coefficient.

[0022] Optionally, the motor parameters include but are not limited to at least one of the following main performance indicators:

[0023] efficiency;

[0024] Torque;

[0025] power;

[0026] resistance.

[0027] Optionally, the step 5 specifically includes:

[0028] Collect the first motor parameter during the operation of the motor, compare the first motor parameter with the second motor parameter obtained by using the motor parameter fusion model, if the difference between the first motor parameter and the second motor parameter is within a threshold range, do not adjust the first motor parameter; if the difference exceeds the threshold range, adjust the first motor parameter according to the second motor parameter.

[0029] A second aspect of the present disclosure provides a motor parameter monitoring model construction system, the system specifically comprising:

[0030] The parameter acquisition module is used to obtain the current motor drive parameters and drive parameter historical data during the operation of the motor;

[0031] A parameter classification module, used for classifying the current motor drive parameters based on the drive parameter history data, and obtaining at least one classification data as basic data for constructing a motor drive parameter model;

[0032] A model building module, used for determining a parameter relationship between each of the classification data and the motor parameter; and building a motor parameter fusion model based on the parameter relationship and the classification data;

[0033] The parameter evaluation module is used to determine and evaluate the motor parameters by using the constructed motor parameter fusion model to obtain the motor parameters during the motor operation process.

[0034] A third aspect of the present disclosure provides a motor parameter monitoring model construction system, comprising: a processor, and a memory communicatively connected to the processor;

[0035] The memory stores computer-executable instructions;

[0036] The processor executes the computer-executable instructions stored in the memory to perform the method as described in any one of the first aspects of the present disclosure.

[0037] The beneficial effect of the present disclosure is that the motor parameter related model constructed by the method and system of the present disclosure can quickly and accurately calculate and evaluate the motor parameters, allowing monitoring personnel to accurately understand the current state of the motor in real time, obtain highly accurate motor parameters during operation, and improve the motor operation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 is a flow chart of a method for constructing a motor parameter monitoring model disclosed in the present invention;

[0039] Figure 2 Schematic diagram of a motor parameter monitoring model construction system disclosed in the present invention. DETAILED DESCRIPTION

[0040] The present disclosure is further described in detail below in conjunction with the accompanying drawings. It is necessary to point out here that the following specific implementation methods are only used to further illustrate the present disclosure and cannot be understood as limiting the scope of protection of the present disclosure. Technical personnel in this field can make some non-essential improvements and adjustments to the present disclosure based on the above application content.

[0041] like Figure 1As shown, a method for constructing a motor parameter monitoring model specifically includes the following steps:

[0042] Step 1: During the operation of the motor, obtain the current motor drive parameters and drive parameter history data.

[0043] The motor driving parameter is an external parameter that drives or affects the operation of the motor, including at least one of a power parameter, an external environment parameter, and a load parameter;

[0044] Wherein, the power parameter includes at least one of voltage and current;

[0045] The external environment parameter includes at least one of temperature and humidity.

[0046] For example, the drive parameter historical data can be the historical data of the above motor drive parameters in the past 5-10 hours, 3-5 days, 1-2 weeks, etc., which can be set according to actual conditions to ensure that there is enough historical data for analysis to achieve the purpose of motor drive parameter classification.

[0047] Step 2: classify the current motor drive parameters based on the drive parameter history data to obtain at least one type of classification data as basic data for constructing the motor drive parameter model.

[0048] For each parameter in the current motor drive parameters, all the drive parameter historical data corresponding to the parameter can be analyzed to obtain the change law of the parameter; then, the current motor drive parameters can be classified according to the change law of each parameter to obtain at least one classification data.

[0049] The change rule may include at least one of the following situations:

[0050] Regular changes, each data in the parameters of the regular changes satisfies the relationship corresponding to the parameters, that is, it can be roughly deduced and calculated through a certain relationship, and when the motor is in a non-fault state, the parameters of the regular changes are within the first expected parameter range;

[0051] Irregular changes: Irregularly changing parameters are usually irregular and are irregular parameters. Among the regularly changing parameters, there is at least one parameter where the difference between two data is greater than the difference threshold. Within a certain range, there may be a certain probability for each value to appear.

[0052] No change: the difference between each data in the unchanged parameter is not greater than the difference threshold, that is, the unchanged parameter is usually constant, or has only a slight change that does not affect the normal operation of the motor.

[0053] For example, in an outdoor environment, the temperature usually follows a certain pattern of change. For example, if the current temperature is 20 degrees, it rises continuously to 35 degrees, and then drops continuously to 20 degrees. At this time, the temperature parameter belongs to the regular change parameter classification; and the humidity may occasionally change drastically depending on the weather. For example, the humidity is 20 on a sunny day, and changes to 80 due to rain. At this time, the humidity belongs to the irregular change parameter classification; and when the current load remains unchanged, the load-related values ​​will not change significantly, so the same load belongs to the unchanged parameter classification during the operation of the motor.

[0054] It is worth noting that some parameters belong to different parameter categories under different application states. For example, when the motor needs to run stably, the input voltage will be set to a fixed value. At this time, the voltage belongs to the category of non-changing parameters. When the motor needs to run under different loads or conditions, different voltage values ​​will be input to calculate and analyze the motor status. At this time, the voltage belongs to the category of regularly changing parameters.

[0055] Step 3, determining the parameter relationship between each type of classification data and the motor parameters, and the parameter relationship can be used for prediction and evaluation of the motor parameters.

[0056] Among them, the motor parameters include but are not limited to at least one of the following main performance indicators:

[0057] efficiency;

[0058] Torque;

[0059] power;

[0060] resistance.

[0061] It should be noted that the parameter relationship includes at least one of the following situations:

[0062] In the first case, the motor parameters are determined by regularly changing parameters and transformation sequences;

[0063] Among them, the transformation sequence S is obtained based on the historical data of regularly changing drive parameters, which can be S (Q1 / Q, Q2 / Q, Q3 / Q..., Q, Q10, Q11...), Q is the current motor drive parameter value, Q1, Q2, Q3... are the historical data of each drive parameter, so the transformation sequence S reflects the law of parameter change.

[0064] For example, when the input voltage and current remain unchanged, the change of the motor torque T is related to the change of temperature W. The temperature transformation sequence S can be used to calculate the motor torque T. W (0.5, 0.7, 1, 1.5, 2, 2.5, 3, 2.5, 2.1.5, 1, 0.7, 0.5), the temperature change sequence S WThe maximum value is 3 and the minimum value is 0.5, so the range of the motor torque T is within T max =3T and T min =0.5T; where T max Refers to the maximum change value of the motor torque T, T min Refers to the minimum change value of motor torque T.

[0065] In the second case, the motor parameters are determined by irregularly changing parameters and probability matrices and parameter conversion formulas;

[0066] For example, the parameter conversion formula can be ;

[0067] Where E is the predicted or required motor parameter, Ex is the motor drive parameter at the current or previous moment, and k1 is the proportional coefficient used when calculating the motor parameter corresponding to the irregularly changing parameter;

[0068] Among them, P is the change matrix, as shown in the following formula:

[0069]

[0070] in, P 00 , P 01 , P 11 , ... are the probabilities of different values ​​of the irregularly changing parameters, which can be obtained by statistics of a large number of driving parameter historical data corresponding to the irregularly changing parameters.

[0071] Therefore, the motor parameter E corresponding to the irregularly changing parameter is obtained by the probability of the value of the corresponding motor drive parameter under certain conditions and the proportionality coefficient used when calculating the motor parameter corresponding to the irregularly changing parameter.

[0072] In the third case, the motor parameters are determined by the constant parameters and the proportionality coefficients used when calculating the motor parameters corresponding to the constant parameters;

[0073] Among them, the proportional coefficient used when calculating the motor parameters corresponding to the unchanged parameters can be determined by actual practice;

[0074] For example, for a fixed load L, the motor output power ; Where k2 is the proportional coefficient for calculating the output power.

[0075] Step 4: Based on the parameter relationship and classification data, a motor parameter fusion model is constructed, which can be used to determine and evaluate the motor parameters.

[0076] The formula used by the motor parameter fusion model may be, for example:

[0077]

[0078] Among them, E(S) represents the motor parameters calculated by analysis based on the transformation sequence S; Ex(P) represents the motor parameters calculated based on the probability matrix P; a, b, and c are model factors, all of which are values ​​between 0 and 1. If a is 0, it means that there are no unchanged parameters when calculating the motor parameter E, if b is 0, it means that there are no regularly changing parameters when calculating the motor parameter E, and if c is 0, it means that there are no irregularly changing parameters when calculating the motor parameter E.

[0079] Therefore, the motor parameter E may be calculated from a single classification parameter, such as , such as motor power calculated by fixed input voltage and current values; it may also be calculated by multiple classification parameters, such as ,or,

[0080] For example, the motor torque is calculated through comprehensive analysis of input voltage, input current and ambient temperature.

[0081] Step 5: Use the constructed motor parameter fusion model to determine and evaluate the motor parameters, obtain the motor parameters during the motor operation process with high accuracy, and improve the motor operation efficiency.

[0082] Collect the first motor parameters during the operation of the motor, compare the first motor parameters with the second motor parameters obtained by using the motor parameter fusion model, and if the difference between the first motor parameters and the second motor parameters is within a threshold range, do not adjust the first motor parameters; if the difference exceeds the threshold range, adjust the first motor parameters according to the second motor parameters.

[0083] In order to implement the above embodiments, the present disclosure also provides a motor parameter monitoring model construction system, such as Figure 2 As shown, the motor parameter monitoring model construction system specifically includes:

[0084] The parameter acquisition module 201 is used to obtain the current motor drive parameters and drive parameter history data during the operation of the motor;

[0085] A parameter classification module 202 is used to classify the current motor drive parameters based on the drive parameter history data, and obtain at least one classification data as basic data for constructing the motor drive parameter model;

[0086] A model building module 203 is used to determine the parameter relationship between each type of classification data and the motor parameter; based on the parameter relationship and the classification data, a motor parameter fusion model is built;

[0087] The parameter evaluation module 204 is used to determine and evaluate the motor parameters by using the constructed motor parameter fusion model to obtain the motor parameters during the operation of the motor.

[0088] Optionally, the motor driving parameters are external parameters that drive or affect the operation of the motor, including at least one of power parameters, external environmental parameters and load parameters, wherein the power parameters include voltage and current; and the external environmental parameters include temperature and humidity.

[0089] Optionally, the parameter classification module 202 is specifically used for:

[0090] For each parameter of the current motor drive parameter, analyze all the historical data of the drive parameters corresponding to the parameter to obtain the change law of the parameter;

[0091] The current motor drive parameters are classified according to the change rule of each parameter to obtain at least one classification data.

[0092] Optionally, the change rule includes at least one of the following situations:

[0093] Regular changes, each data in the regularly changing parameters satisfies the relationship corresponding to the parameters, and when the motor is in a non-fault state, the parameters are within a first expected parameter range;

[0094] Irregular changes: irregularly changing parameters are irregular parameters, and among the regularly changing parameters, the difference between at least two data is greater than the difference threshold;

[0095] No change: the difference between each data in the unchanged parameter is not greater than the difference threshold.

[0096] Optional parameter relationship, including at least one of the following:

[0097] The motor parameters are determined by regularly changing parameters and transformation sequences;

[0098] The motor parameters are determined by irregularly changing parameters and probability matrices and parameter conversion formulas;

[0099] The motor parameters are determined by the constant parameters and the proportional coefficient.

[0100] Optionally, the motor parameters include but are not limited to at least one of the following main performance indicators:

[0101] efficiency;

[0102] Torque;

[0103] power;

[0104] resistance.

[0105] Optionally, the parameter evaluation module 204 is specifically used for:

[0106] Collect the first motor parameters during the operation of the motor, compare the first motor parameters with the second motor parameters obtained by using the motor parameter fusion model, and if the difference between the first motor parameters and the second motor parameters is within a threshold range, do not adjust the first motor parameters; if the difference exceeds the threshold range, adjust the first motor parameters according to the second motor parameters.

[0107] It should be noted that the above explanation of the motor parameter monitoring model construction method embodiment is also applicable to the motor parameter monitoring model construction system of this embodiment, and will not be repeated here.

[0108] In order to implement the above embodiments, the present disclosure also proposes a motor parameter monitoring model construction system, including: a processor, and a memory connected to the processor for communication; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the method provided by the above embodiments.

[0109] The above embodiments only express several implementation methods of the present disclosure, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present disclosure. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present disclosure, and these all belong to the protection scope of the present disclosure.

Claims

1. A method for constructing a motor parameter monitoring model, characterized in that: The method specifically comprises the steps of: Step 1, during the operation of the motor, obtaining current motor drive parameters and drive parameter history data; Step 2: classify the current motor drive parameters based on the drive parameter history data to obtain at least one classification data as basic data for constructing a motor drive parameter model; Step 3, determining a parameter relationship between each of the classification data and the motor parameters; Step 4, constructing a motor parameter fusion model based on the parameter relationship and the classification data; Step 5, using the constructed motor parameter fusion model to determine and evaluate the motor parameters to obtain the motor parameters during the motor operation process; The step 2 specifically includes: For each parameter of the current motor drive parameter, analyzing all drive parameter historical data corresponding to the parameter to obtain a change rule of the parameter; Classify the current motor drive parameters according to the change rule of each parameter to obtain at least one classification data; The change rule includes at least one of the following situations: Regular changes, each data in the parameter of the regular changes satisfies a relational expression corresponding to the parameter, and when the motor is in a non-fault state, the parameter is within a first expected parameter range; Irregular changes, the irregularly changing parameters are irregular parameters, and the difference between at least two data in the regularly changing parameters is greater than the difference threshold; No change, the difference between each data in the unchanged parameter is not greater than the difference threshold; The parameter relationship includes at least one of the following situations: The motor parameters are determined by the regularly changing parameters and the transformation sequence; The motor parameters are determined by the irregularly changing parameters and probability matrix and parameter conversion formula; The motor parameters are determined by the unchanged parameters and a proportionality coefficient.

2. The method for constructing a motor parameter monitoring model according to claim 1, characterized in that: The motor driving parameters are external parameters that drive or affect the operation of the motor, including at least one of power parameters, external environmental parameters and load parameters, wherein the power parameters include voltage and current; the external environmental parameters include temperature and humidity.

3. The method for constructing a motor parameter monitoring model according to claim 1, characterized in that: The motor parameters include but are not limited to at least one of the following main performance indicators: efficiency; Torque; power; resistance.

4. The method for constructing a motor parameter monitoring model according to claim 1, characterized in that: The step 5 specifically includes: Collect the first motor parameter during the operation of the motor, compare the first motor parameter with the second motor parameter obtained by using the motor parameter fusion model, if the difference between the first motor parameter and the second motor parameter is within a threshold range, do not adjust the first motor parameter; if the difference exceeds the threshold range, adjust the first motor parameter according to the second motor parameter.

5. A motor parameter monitoring model construction system, characterized in that: The system specifically comprises: The parameter acquisition module is used to obtain the current motor drive parameters and drive parameter historical data during the operation of the motor; A parameter classification module, used for classifying the current motor drive parameters based on the drive parameter history data, and obtaining at least one classification data as basic data for constructing a motor drive parameter model; A model building module, used for determining a parameter relationship between each of the classification data and the motor parameter; and building a motor parameter fusion model based on the parameter relationship and the classification data; A parameter evaluation module, used to determine and evaluate the motor parameters by using the constructed motor parameter fusion model, and obtain the motor parameters during the motor operation process; The parameter classification module is specifically used for: For each parameter of the current motor drive parameter, analyzing all drive parameter historical data corresponding to the parameter to obtain a change rule of the parameter; Classify the current motor drive parameters according to the change rule of each parameter to obtain at least one classification data; The change rule includes at least one of the following situations: Regular changes, each data in the parameter of the regular changes satisfies a relational expression corresponding to the parameter, and when the motor is in a non-fault state, the parameter is within a first expected parameter range; Irregular changes, the irregularly changing parameters are irregular parameters, and the difference between at least two data in the regularly changing parameters is greater than the difference threshold; No change, the difference between each data in the unchanged parameter is not greater than the difference threshold; The parameter relationship includes at least one of the following situations: The motor parameters are determined by the regularly changing parameters and the transformation sequence; The motor parameters are determined by the irregularly changing parameters and probability matrix and parameter conversion formula; The motor parameters are determined by the unchanged parameters and a proportionality coefficient.

6. A motor parameter monitoring model construction system, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to perform the method according to any one of claims 1 to 4.

Images