A frequency converter energy-saving control method and system

Abstract

The present application discloses a frequency converter energy-saving control method and system, and the present application belongs to the field of frequency converter control. The method comprises: calculating the load membership of the first load data in each load range and the speed error membership of the first speed error in each speed error range at the first monitoring time point; calculating the comprehensive membership of each frequency adjustment rule in the frequency adjustment rule set; calculating the frequency adjustment value, and transmitting the frequency adjustment value to the frequency converter; the scheme adjusts the operating frequency of the motor according to the actual data of the load and speed error, avoiding the motor from running at an unnecessary high speed, thereby reducing energy waste and increasing the flexibility of adjustment. By calculating the comprehensive membership of the load and speed errors, the adjustment accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the field of inverter control technology, and in particular to an inverter energy-saving control method and system. Background Art

[0002] Conventional motors usually run at a fixed speed, consuming the same amount of energy regardless of load. This mode of operation results in significant energy waste when the motor is lightly loaded or unloaded. The inverter controls the motor speed by changing the power supply frequency, allowing the motor to adjust its output power according to the actual load demand, thereby achieving significant energy savings. When the load demand decreases, energy consumption can be greatly reduced by reducing the motor speed.

[0003] Nowadays, the output frequency of the inverter is adjusted according to preset fixed parameters, such as load threshold and speed threshold. When the load or speed exceeds a certain threshold, the inverter automatically adjusts the frequency to maintain or change the operating state of the motor.

[0004] However, due to the relatively simple control strategy, the output frequency of the inverter cannot be accurately adjusted according to the real-time load and speed changes, causing the motor to run in a non-optimal state for part of the time, thereby increasing energy consumption. In addition, the adaptability is poor and effective adjustments cannot be made in time, resulting in low control accuracy. Summary of the invention

[0005] The embodiment of the present application provides an inverter energy-saving control method and system, which solves the problem in the prior art that the inverter control strategy is relatively simple and the output frequency of the inverter cannot be accurately adjusted according to the real-time load and speed changes, resulting in the motor running in a non-optimal state for part of the time, thereby increasing energy consumption. In addition, the adaptability is poor and effective adjustments cannot be made in time, resulting in low control accuracy.

[0006] In a first aspect, an embodiment of the present application provides a frequency converter energy-saving control method, the method comprising:

[0007] Acquire first load data and a first speed error of the motor at a first monitoring time point, and calculate the load membership of the first load data in each load range according to the first load data and a preset load membership calculation formula set;

[0008] Calculating the speed error membership of the first speed error in each speed error range according to the first speed error and a preset speed error membership calculation formula set;

[0009] Obtaining a preset frequency adjustment rule set and a preset comprehensive membership calculation rule, and calculating the comprehensive membership of each frequency adjustment rule in the frequency adjustment rule set according to the load membership, the speed error membership, the preset frequency adjustment rule set and the preset comprehensive membership calculation rule;

[0010] Obtain the comprehensive adjustment frequency of each frequency adjustment rule in the preset frequency adjustment rule set, calculate the frequency adjustment value according to the comprehensive membership, the comprehensive adjustment frequency and the preset frequency adjustment formula, and transmit the frequency adjustment value to the frequency converter, so that the frequency converter adjusts the output frequency according to the frequency adjustment value, thereby controlling the operating frequency of the motor; wherein the preset frequency adjustment formula is:

[0011]

[0012] Among them, FA is the frequency adjustment value; u i is the comprehensive membership degree of the ith frequency adjustment rule; z i is the comprehensive adjustment frequency of the ith frequency adjustment rule; ∑ i (u i ·z i ) is the weighted sum of the comprehensive membership of all frequency adjustment rules and the corresponding comprehensive adjustment frequencies; ∑ i u i It is the sum of the comprehensive membership of all frequency adjustment rules.

[0013] Furthermore, after transmitting the frequency adjustment value to the frequency converter, the method further includes:

[0014] Acquire current environmental data, input the first load data, the first speed error and the current environmental data into a preset prediction model to obtain predicted load data and predicted speed error;

[0015] Calculating the predicted load membership of the predicted load data in each load range according to the predicted load data and a preset load membership calculation formula set;

[0016] Calculating the predicted speed error membership of the predicted speed error in each speed error range according to the predicted speed error and a preset speed error membership calculation formula set;

[0017] Calculate the comprehensive predicted membership of each frequency adjustment rule in the frequency adjustment rule set according to the predicted load membership, the predicted speed error membership, the preset frequency adjustment rule set and the preset comprehensive membership calculation rule;

[0018] Calculating a prediction frequency adjustment value according to the comprehensive prediction membership, the comprehensive adjustment frequency and a preset prediction frequency adjustment formula;

[0019] Before reaching an adjacent second monitoring time point, obtaining second load data and a second speed error in real time, calculating a first load data change value of the first load data and the second load data, and calculating a first speed error change value of the first speed error and the second speed error;

[0020] Obtain a preset load weight, a preset speed error weight, a preset load weight calculation formula, and a preset speed error weight calculation formula, and calculate a first load weighted value of the first load data change value according to the first load data change value and the preset load weight calculation formula; wherein the preset load weight calculation formula is:

[0021] Load Weighted Value=PLW×LDVV;

[0022] Among them, Load Weighted Value is the load weighted value; PLW is the preset load weight; LDVV is the load data change value;

[0023] According to the first speed error change value and a preset speed error weight calculation formula, a first speed error weighted value of the first speed error change value is calculated; wherein the preset speed error weight calculation formula is:

[0024] Speed ​​Error Weighted Value=PSE*SEV;

[0025] Among them, Speed ​​Error Weighted Value is the speed error weighted value; PSE is the preset speed error; SEV is the speed error change value;

[0026] Obtain a preset weighted sum calculation formula, and calculate a first weighted sum of the first load weighted value and the first speed error weighted value according to the first load weighted value, the first speed error weighted value, and the preset weighted sum calculation formula; wherein the preset weighted sum calculation formula is:

[0027] Weighted Sum = LWV + SEWV;

[0028] Among them, Weighted Sum is the weighted sum; LWV is the load weighted value; SEWV is the speed error weighted value;

[0029] If the first weighted sum exceeds a preset weighted sum threshold before reaching an adjacent second monitoring time point, the predicted frequency adjustment value is transmitted to the frequency converter so that the frequency converter adjusts the output frequency according to the predicted frequency adjustment value.

[0030] Further, after calculating the first weighted sum of the first load weighted value and the first speed error weighted value, the method further includes:

[0031] If the first weighted sum does not exceed the preset weighted sum threshold before reaching the adjacent second monitoring time point, then when reaching the adjacent second monitoring time point, the third load data and the third speed error are obtained, and a second load data change value of the first load data and the third load data is calculated, and a second speed error change value of the first speed error and the third speed error is calculated;

[0032] Calculating a second load weighted value of the second load data change value according to the second load data change value and a preset load weight calculation formula;

[0033] Calculating a second speed error weighted value of the second speed error change value according to the second speed error change value and a preset speed error weight calculation formula;

[0034] Calculating a second weighted sum of the second load weighted value and the second speed error weighted value according to the second load weighted value, the second speed error weighted value and a preset weighted sum calculation formula;

[0035] If the second weighted sum exceeds a preset weighted sum threshold, the predicted frequency adjustment value is transmitted to the frequency converter, so that the frequency converter adjusts the output frequency according to the predicted frequency adjustment value.

[0036] Furthermore, the training process of the preset prediction model includes:

[0037] Acquire historical environmental data, historical load data, and historical speed errors at different monitoring time points, and create a first data set according to the monitoring time points, the historical environmental data, the historical load data, and the historical speed errors;

[0038] Constructing a prediction model, and training the prediction model according to the first data set until the prediction model reaches a preset prediction model training standard.

[0039] Further, after calculating the second weighted sum of the second load weighted value and the second speed error weighted value, the method further includes:

[0040] If the second weighted sum does not exceed a preset weighted sum threshold, the preset prediction model is retrained according to the third load data and the third speed error until the prediction model reaches a preset prediction model training standard.

[0041] Furthermore, after transmitting the frequency adjustment value to the frequency converter, the method further includes:

[0042] Obtaining electrical parameters, mechanical parameters, environmental parameters, operating parameters, and energy consumption parameters of the inverter, inputting the electrical parameters, mechanical parameters, environmental parameters, operating parameters, and energy consumption parameters into a preset fault identification model to obtain a fault risk score, and determining whether the inverter has a fault risk according to the fault risk score and a preset risk score threshold;

[0043] If there is a risk of failure, the cause of the failure is determined based on a preset fault identification model, and the cause of the failure is sent to the control center for staff to troubleshoot and repair the failure based on the cause of the failure.

[0044] Furthermore, the training process of the preset fault identification model includes:

[0045] Acquire historical electrical parameters, historical mechanical parameters, historical environmental parameters, historical operating parameters, historical energy consumption parameters, historical fault causes, and historical fault risk scores of the frequency converter, and create a second data set based on the historical electrical parameters, historical mechanical parameters, historical environmental parameters, historical operating parameters, historical energy consumption parameters, historical fault causes, and historical fault risk scores;

[0046] A fault identification model is constructed, and the fault identification model is trained according to the second data set until the fault identification model reaches a preset fault identification model training standard.

[0047] Furthermore, after constructing the fault identification model and training the fault identification model according to the second data set until the fault identification model reaches a preset fault identification model training standard, the method further includes:

[0048] If the preset model update time interval is reached, the historical electrical parameters, historical mechanical parameters, historical environmental parameters, historical operating parameters, historical energy consumption parameters, historical fault causes and historical fault risk scores of the inverter are collected again, and the second data set is updated. The fault identification model is retrained according to the updated second data set until the fault identification model meets the preset fault identification model training standard.

[0049] Furthermore, the preset load membership calculation formula set includes:

[0050] Low load membership formula:

[0051]

[0052] Among them, μ Low (Load) is the load membership of the load data in the low-load fuzzy set; Load is the load data; is the low load membership of the load data in the low load set. The lower the load, the higher the low load membership. Ensure that the load membership is within the range of [0, 1] and cannot be lower than 0 or higher than 1; and when the load data is lower than 5, the load membership is 1;

[0053] Medium load membership formula:

[0054]

[0055] Among them, μ Medium (Load) is the load membership of load data in the medium load fuzzy set; Load is the load data; is the medium load membership of the load data in the medium load interval. The closer the load data is to 5, the higher the medium load membership is. The medium load membership degree is calculated for another part of the load data in the medium load interval. The closer the load data is to 10, the higher the medium load membership degree is. Ensure that the load membership is within the range of [0, 1] and the load membership cannot be lower than 0 or higher than 1;

[0056] High load membership formula:

[0057]

[0058] Among them, μ High (Load) is the load membership of the load data in the high-load fuzzy set; Load is the load data; is the high load membership of the load data in the high load interval. The higher the load data, the higher the high load membership. Ensure that the load membership is in the range of [0, 1] and cannot be lower than 0 or higher than 1; and the maximum value of the high load membership in the high load interval is 1. When the load data is lower than 5, the high load membership is 0.

[0059] According to a second aspect of the present application, a frequency converter energy-saving control system is provided, the system comprising:

[0060] A load membership calculation module, used to obtain first load data and a first speed error of the motor at a first monitoring time point, and calculate the load membership of the first load data in each load range according to the first load data and a preset load membership calculation formula set;

[0061] A speed error membership calculation module, used to calculate the speed error membership of the first speed error in each speed error range according to the first speed error and a preset speed error membership calculation formula set;

[0062] A comprehensive membership calculation module, used to obtain a preset frequency adjustment rule set, and calculate the comprehensive membership of each frequency adjustment rule in the frequency adjustment rule set according to the load membership, the speed error membership, the preset frequency adjustment rule set and the preset comprehensive membership calculation rule;

[0063] The output frequency adjustment module is used to obtain the comprehensive adjustment frequency of each frequency adjustment rule in the preset frequency adjustment rule set, calculate the frequency adjustment value according to the comprehensive membership, the comprehensive adjustment frequency and the preset frequency adjustment formula, and transmit the frequency adjustment value to the frequency converter, so that the frequency converter adjusts the output frequency according to the frequency adjustment value, thereby controlling the operating frequency of the motor; wherein the preset frequency adjustment formula is:

[0064]

[0065] Among them, FA is the frequency adjustment value; u i is the comprehensive membership degree of the ith frequency adjustment rule; z i is the comprehensive adjustment frequency of the ith frequency adjustment rule; ∑ i (u i ·z i ) is the weighted sum of the comprehensive membership of all frequency adjustment rules and the corresponding comprehensive adjustment frequencies; ∑ i u i It is the sum of the comprehensive membership of all frequency adjustment rules.

[0066] In an embodiment of the present application, first load data and a first speed error of the motor are obtained at a first monitoring time point, and the load membership of the first load data in each load range is calculated according to the first load data and a preset load membership calculation formula set; the speed error membership of the first speed error in each speed error range is calculated according to the first speed error and a preset speed error membership calculation formula set; a preset frequency adjustment rule set and a preset comprehensive membership calculation rule are obtained, and the comprehensive membership of each frequency adjustment rule in the frequency adjustment rule set is calculated according to the load membership, the speed error membership, the preset frequency adjustment rule set and the preset comprehensive membership calculation rule; the comprehensive adjustment frequency of each frequency adjustment rule in the preset frequency adjustment rule set is obtained, and the frequency adjustment value is calculated according to the comprehensive membership, the comprehensive adjustment frequency and the preset frequency adjustment formula, and the frequency adjustment value is transmitted to the inverter, so that the inverter adjusts the output frequency according to the frequency adjustment value, thereby controlling the running frequency of the motor; wherein the preset frequency adjustment formula is:

[0067]

[0068] Among them, FA is the frequency adjustment value; u iis the comprehensive membership degree of the ith frequency adjustment rule; z i is the comprehensive adjustment frequency of the ith frequency adjustment rule; ∑ i (u i ·z i ) is the weighted sum of the comprehensive membership of all frequency adjustment rules and the corresponding comprehensive adjustment frequencies; ∑ i u i The sum of the comprehensive membership of all frequency adjustment rules. Through the above inverter energy-saving control method, the operating frequency of the motor is adjusted according to the actual data of the load and speed error, which avoids the motor running at an unnecessary high speed, thereby reducing energy waste and increasing the flexibility of adjustment. By calculating the comprehensive membership of the load and speed errors, the adjustment accuracy can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 It is a flowchart of the inverter energy-saving control method provided in Example 1 of the present application;

[0070] Figure 2 It is a flow chart of the inverter energy-saving control method provided in the second embodiment of the present application;

[0071] Figure 3 It is a flowchart of the inverter energy-saving control method provided in Embodiment 3 of the present application;

[0072] Figure 4 It is a structural schematic diagram of the inverter energy-saving control system provided in Embodiment 4 of the present application; DETAILED DESCRIPTION

[0073] In order to make the purpose, technical scheme and advantages of the present application clearer, the specific embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. It is understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for the convenience of description, only the part related to the present application but not all the contents are shown in the accompanying drawings. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow chart describes each operation (or step) as a sequential process, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of each operation can be rearranged. The process can be terminated when its operation is completed, but it can also have additional steps not included in the accompanying drawings. The process can correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.

[0074] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0075] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0076] The energy-saving control method for the frequency converter provided in the embodiment of the present application is described in detail below through specific embodiments and application scenarios in conjunction with the accompanying drawings.

[0077] Embodiment 1

[0078] Figure 1 1 is a flow chart of the inverter energy-saving control method provided in the first embodiment of the present application. Figure 1 As shown, the specific steps include:

[0079] S101, obtaining first load data and a first speed error of the motor at a first monitoring time point, and calculating the load membership of the first load data in each load range according to the first load data and a preset load membership calculation formula set.

[0080] First, the usage scenario of this solution can be to collect the load data and speed error of the motor during the monitoring time point, thereby calculating the adjustment frequency of the inverter, and transmitting the adjustment frequency to the inverter to control the operating frequency of the motor.

[0081] Based on the above usage scenarios, it can be understood that the executor of the present application can be a frequency converter energy-saving control system, and no excessive limitations are made here.

[0082] The first monitoring time point may be the time point at which the system starts to collect data. At this time point, the system will collect relevant operating data.

[0083] The electric motor may be an electric motor controlled by a frequency converter, and specifically, may be an AC asynchronous motor or other types of electric motors.

[0084] The first load data may be the load borne by the motor at the first monitoring time point, for example, the output power of the motor.

[0085] The first speed error can be the difference between the actual speed of the motor and the target speed at the first monitoring time point. At each monitoring time point, the target speed of the current cycle can be preset in advance, and the speed error can be calculated by the difference between the set value and the actual measured value.

[0086] The preset load membership calculation formula set can be used to calculate the fuzzy membership function set of the motor load membership within different load ranges. These formulas are set in advance and can include membership functions such as low load, medium load and high load.

[0087] The load range may be a classification range of the motor load, and specifically may include low load (0-20%), medium load (20%-70%), high load (70%-100%), and the like.

[0088] The load membership may be a membership value of the motor load within different load ranges. Specifically, it may be a value between 0 and 1, which is used to indicate the degree to which the current load data belongs to a certain load range.

[0089] At the first monitoring time point, the load data (such as power, torque, etc.) and speed error (the difference between the actual speed and the target speed) of the motor can be collected. If the target speed is fixed, the target speed can be set when the system is initialized. If the target speed is dynamic, the target speed needs to be calculated by an algorithm or control strategy at the beginning of each monitoring time point. Then, the preset load membership calculation formula set is used to calculate the membership of the first load data in each load range.

[0090] On the basis of the above technical solution, an optional, preset set of load membership calculation formulas includes:

[0091] Low load membership formula:

[0092]

[0093] Among them, μ Low (Load) is the load membership of the load data in the low-load fuzzy set; Load is the load data; is the low load membership of the load data in the low load set. The lower the load, the higher the low load membership. Ensure that the load membership is within the range of [0, 1] and cannot be lower than 0 or higher than 1; and when the load data is lower than 5, the load membership is 1;

[0094] Medium load membership formula:

[0095]

[0096] Among them, μ Medium (Load) is the load membership of load data in the medium load fuzzy set; Load is the load data; is the medium load membership of the load data in the medium load interval. The closer the load data is to 5, the higher the medium load membership is. The medium load membership degree is calculated for another part of the load data in the medium load interval. The closer the load data is to 10, the higher the medium load membership degree is. Ensure that the load membership is within the range of [0, 1] and the load membership cannot be lower than 0 or higher than 1;

[0097] High load membership formula:

[0098]

[0099] Among them, μ High (Load) is the load membership of the load data in the high-load fuzzy set; Load is the load data; is the high load membership of the load data in the high load interval. The higher the load data, the higher the high load membership. Ensure that the load membership is in the range of [0, 1] and cannot be lower than 0 or higher than 1; and the maximum value of the high load membership in the high load interval is 1. When the load data is lower than 5, the high load membership is 0.

[0100] In this solution, at the first monitoring time point, Load is the first load data, μ Low (Load), μ Medium (Load), μ High (Load) is the load membership of the first load data in the corresponding load interval; at the second monitoring time point, Load is the predicted load data, μ Low (Load), μ Medium (Load), μ High (Load) is the predicted load membership of the predicted load data in the corresponding load interval.

[0101] S102: Calculate the speed error membership of the first speed error in each speed error range according to the first speed error and a preset speed error membership calculation formula set.

[0102] The preset speed error membership calculation formula set can be used to convert the speed error into a membership value to indicate its degree of membership in different speed error ranges (which may include negative large, negative medium, negative small, zero, positive small, positive medium, and positive large). This process involves mapping the actual speed error to a fuzzy set and calculating the membership in each set through a membership function.

[0103] The preset speed error membership calculation formula set includes:

[0104] Negative big:

[0105]

[0106] Among them, μ NB (SE) is the speed error membership in the negative large fuzzy set; SE is the speed error; Lower Bound NB The lower bound of the predefined negative large fuzzy set; Upper Bound NB is the upper limit value of the predefined negative large fuzzy set;

[0107] Negative:

[0108]

[0109] Among them, μ NM (SE) is the speed error membership in the negative-mode fuzzy set; SE is the speed error; Lower Bound NM The lower bound of the predefined negative-mean fuzzy set; Upper Bound NM Peak is the upper limit of the predefined negative-mean fuzzy set; NM is the peak value of the predefined negative-mean fuzzy set;

[0110] zero:

[0111]

[0112] Among them, μ ZE (SE) is the speed error membership in the zero fuzzy set; SE is the speed error; Lower Bound ZE The lower bound of the predefined zero fuzzy set; Upper Bound ZE Peak is the upper limit of the predefined zero fuzzy set; ZE is the peak value of the predefined zero fuzzy set;

[0113] middle:

[0114]

[0115]

[0116] Among them, μ PM (SE) is the speed error membership in the median fuzzy set; SE is the speed error; Lower Bound PM The lower limit of the predefined median fuzzy set; Upper Bound PM Peak is the upper limit of the predefined median fuzzy set; PM is the peak value of the predefined median fuzzy set;

[0117] Zhengda:

[0118]

[0119] Among them, μ NB (SE) is the speed error membership in the positive fuzzy set; SE is the speed error; Lower Bound NB The lower bound of the positive fuzzy set predefined in advance; Upper Bound NB It is the upper limit value of the positive fuzzy set predefined in advance.

[0120] In this scheme, at the first monitoring time point, SE is the first speed error, μ NB (SE), μ NM (SE), μ ZE (SE), μ PM (SE), μ PB (SE) is the speed error membership of the first speed error in the corresponding fuzzy set; at the second monitoring time point, SE is the predicted speed error, μ NB (SE), μ NM (SE), μ ZE (SE), μ PM (SE), μ PB (SE) is the predicted speed error membership in the corresponding fuzzy set.

[0121] The speed error range may refer to the interval of speed error values ​​covered by the fuzzy sets (which may include negative large, negative medium, negative small, zero, positive small, positive medium, and positive large) used to define the speed error in the fuzzy logic control system. These ranges are usually set based on the characteristics and control requirements of the actual system, specifically representing the distribution of speed errors in different fuzzy sets. The speed error range is also called a fuzzy set.

[0122] The speed error membership can indicate the degree to which the speed error value belongs to a certain fuzzy set, and its value range is 0 to 1. The higher the membership, the more the speed error value conforms to the characteristics of the fuzzy set.

[0123] The first speed error may be substituted into a preset speed error membership calculation formula set to calculate the speed error membership of the first speed error in different speed error ranges.

[0124] S103, obtaining a preset frequency adjustment rule set and a preset comprehensive membership calculation rule, and calculating the comprehensive membership of each frequency adjustment rule in the frequency adjustment rule set according to the load membership, the speed error membership, the preset frequency adjustment rule set and the preset comprehensive membership calculation rule.

[0125] The preset frequency adjustment rule set may be a set of fuzzy logic rules for adjusting the operating frequency of the motor according to the load membership and the speed error membership. These rules may generally be derived from expert experience or system characteristics in order to optimize the performance of the system.

[0126] Specifically, the preset frequency adjustment rule set may be:

[0127] Rule 1: If the load is low and the speed error is large and negative, the frequency adjustment is large and positive.

[0128] Rule 2: If the load is low and the speed error is negative, the frequency adjustment amount is small.

[0129] Rule 3: If the load is low and the speed error is zero, the frequency adjustment is unchanged.

[0130] Rule 4: If the load is low and the speed error is neutral, the frequency adjustment should be reduced.

[0131] Rule 5: If the load is low and the speed error is positive, the frequency adjustment is negative.

[0132] Rule 6: If the load is medium and the speed error is negative and large, the frequency adjustment amount is small.

[0133] Rule 7: If the load is medium and the speed error is negative medium, the frequency adjustment amount is unchanged.

[0134] Rule 8: If the load is medium and the speed error is zero, the frequency adjustment is unchanged.

[0135] Rule 9: If the load is medium and the speed error is medium, the frequency adjustment amount is unchanged.

[0136] Rule 10: If the load is medium and the speed error is positive, the frequency adjustment amount is reduced.

[0137] Rule 11: If the load is high and the speed error is large and negative, the frequency adjustment amount is unchanged.

[0138] Rule 12: If the load is high and the speed error is negative, the frequency adjustment amount is reduced.

[0139] Rule 13: If the load is high and the speed error is zero, the frequency adjustment is reduced.

[0140] Rule 14: If the load is high and the speed error is medium, the frequency adjustment is large.

[0141] Rule 15: If the load is high and the speed error is positive, the frequency adjustment is negative.

[0142] The preset comprehensive membership calculation rule may refer to determining the activation of each rule by the minimum membership value of the input variable. This is the role of the "min" operation. Specifically, for each fuzzy rule, the membership of the input variable in each fuzzy set can be calculated. For example, the membership of the load being "medium" and the membership of the speed error being "center" are calculated. For each fuzzy rule, the minimum value of the input variable membership is taken as the activation of the rule. This operation is implemented by the min operation. For example, for the rule "If the load is low and the speed error is negative and large, the frequency decreases", if the load membership is 0.7 and the speed error membership is 0.5, then the comprehensive membership = min(0.7, 0.5) = 0.5.

[0143] The comprehensive membership may refer to the membership of each frequency adjustment rule obtained by combining the load membership and the speed error membership, which indicates the applicability of the rule under the current conditions.

[0144] The preset frequency adjustment rule set and the preset comprehensive membership calculation rule can be read from the database, and then the comprehensive membership of each frequency adjustment rule in the frequency adjustment rule set is calculated through the load membership of the first load data in each load range and the speed error membership of the first speed error in each speed error range. For example, the low load range membership is 0.8, the medium load range membership is 0.2, and the high load range membership is 0. In the speed error range, the membership of the negative large range is 0.5, the membership of the negative medium range is 0.5, the membership of the negative small range is 0, the membership of the zero range is 0, the membership of the positive small range is 0, the membership of the positive medium range is 0, and the membership of the positive large range is 0, then:

[0145] Rule 1: Comprehensive membership = min(load membership_low load (3), speed error membership_negative large (-4)) = min(0.8, 0.5) = 0.5

[0146] Rule 2: Comprehensive membership = min(load membership_low load (3), speed error membership_negative medium (-4)) = min(0.8, 0.5) = 0.5

[0147] By analogy, the comprehensive membership of rules 3-5 is 0, the comprehensive membership of rules 9-15 is 0, and the comprehensive membership of rules 6-7 is 0.2.

[0148] S104, obtaining the comprehensive adjustment frequency of each frequency adjustment rule in the preset frequency adjustment rule set, calculating the frequency adjustment value according to the comprehensive membership, the comprehensive adjustment frequency and the preset frequency adjustment formula, and transmitting the frequency adjustment value to the inverter, so that the inverter adjusts the output frequency according to the frequency adjustment value, thereby controlling the operating frequency of the motor; wherein the preset frequency adjustment formula is:

[0149]

[0150] Among them, FA is the frequency adjustment value; u i is the comprehensive membership degree of the ith frequency adjustment rule; z i is the comprehensive adjustment frequency of the ith frequency adjustment rule; ∑ i (u i ·z i ) is the weighted sum of the comprehensive membership of all frequency adjustment rules and the corresponding comprehensive adjustment frequencies; ∑ i u i It is the sum of the comprehensive membership of all frequency adjustment rules.

[0151] The comprehensive adjustment frequency may refer to the frequency adjustment amount corresponding to each rule according to a preset frequency adjustment rule set. These adjustment amounts are usually determined based on experience or experimental data and represent the frequency adjustment amplitude required under certain load and speed error conditions.

[0152] The preset frequency adjustment formula may be a weighted average of the comprehensive membership of each frequency adjustment rule and the corresponding comprehensive adjustment frequency to obtain a final frequency adjustment value.

[0153] The frequency adjustment value may be a value calculated by the above frequency adjustment formula, which indicates the specific amount of adjustment that should be made to the output frequency of the inverter in order to achieve the required motor operating speed and power.

[0154] The frequency converter can be a device used to adjust the speed and power of the AC motor. By changing the frequency input to the motor, the frequency converter can accurately control the operating state of the motor, thereby achieving the effect of energy saving and optimizing performance.

[0155] The comprehensive adjustment frequency of each frequency adjustment rule in the preset frequency adjustment rule set can be read from the database, and the comprehensive membership and the comprehensive adjustment frequency can be substituted into the preset frequency adjustment formula to obtain the frequency adjustment value, and then the frequency adjustment value can be transmitted to the inverter through wireless communication technology. The inverter adjusts its output frequency according to the received frequency adjustment value, thereby controlling the operating frequency of the motor. For example,

[0156] Rule 1: Comprehensive membership = min(load membership_low load (3), speed error membership_negative large (-4)) = min(0.8, 0.5) = 0.5

[0157] Rule 2: Comprehensive membership = min(load membership_low load (3), speed error membership_negative medium (-4)) = min(0.8, 0.5) = 0.5

[0158] The comprehensive adjustment frequency of rule 1 is 5Hz, and the comprehensive adjustment frequency of rule 2 is 3Hz, so the frequency adjustment value is:

[0159]

[0160] This 4Hz frequency adjustment value is then transmitted to the frequency converter, which adjusts the output frequency by 4Hz to control the operating frequency of the motor.

[0161] In an embodiment of the present application, the first load data and the first speed error of the motor are obtained at a first monitoring time point, and the load membership of the first load data in each load range is calculated according to the first load data and a preset load membership calculation formula set; the speed error membership of the first speed error in each speed error range is calculated according to the first speed error and a preset speed error membership calculation formula set; a preset frequency adjustment rule set and a preset comprehensive membership calculation rule are obtained, and the comprehensive membership of each frequency adjustment rule in the frequency adjustment rule set is calculated according to the load membership, the speed error membership, the preset frequency adjustment rule set and the preset comprehensive membership calculation rule; the comprehensive adjustment frequency of each frequency adjustment rule in the preset frequency adjustment rule set is obtained, and the frequency adjustment value is calculated according to the comprehensive membership, the comprehensive adjustment frequency and the preset frequency adjustment formula, and the frequency adjustment value is transmitted to the inverter, so that the inverter adjusts the output frequency according to the frequency adjustment value, thereby controlling the running frequency of the motor; wherein the preset frequency adjustment formula is:

[0162]

[0163] Among them, FA is the frequency adjustment value; u i is the comprehensive membership degree of the ith frequency adjustment rule; z iis the comprehensive adjustment frequency of the ith frequency adjustment rule; ∑ i (u i ·z i ) is the weighted sum of the comprehensive membership of all frequency adjustment rules and the corresponding comprehensive adjustment frequencies; ∑ i u i The sum of the comprehensive membership of all frequency adjustment rules. Through the above inverter energy-saving control method, the operating frequency of the motor is adjusted according to the actual data of the load and speed error, which avoids the motor running at an unnecessary high speed, thereby reducing energy waste and increasing the flexibility of adjustment. By calculating the comprehensive membership of the load and speed errors, the adjustment accuracy can be improved.

[0164] Embodiment 2

[0165] Figure 2 is a flow chart of the inverter energy-saving control method provided in the second embodiment of the present application, such as Figure 2 As shown, the specific method includes the following steps:

[0166] S201, obtaining current environmental data, inputting the first load data, the first speed error and the current environmental data into a preset prediction model to obtain predicted load data and predicted speed error.

[0167] Current environmental data may refer to data of external and internal environmental factors that affect the operation of the motor, such as temperature, humidity, pressure, actual load of the production line, and working status of the equipment.

[0168] The preset prediction model can be a mathematical or machine learning model based on historical data and statistical analysis, which is used to predict future load data and speed errors. The model makes predictions through input variables (i.e., first load data, first speed error, current environmental data).

[0169] The predicted load data may be an estimate of future load obtained by inputting current load data, speed error, and current environmental data into a prediction model.

[0170] The predicted speed error may be an estimated value of the future speed error obtained by inputting the current speed error, load data, and current environmental data into the prediction model.

[0171] Data on current environmental conditions, such as temperature, humidity, etc., can be collected. Ensure that load data, speed error, and environmental data are input in the format required by the model. For linear regression models, data needs to be standardized or normalized. Input the organized data into the preset prediction model for calculation. The prediction model will generate prediction results based on the input data. The model will output two prediction values: predicted load data and predicted speed error. These results represent the possible load and speed errors of the system at a specific point in time in the future. In this solution, the specific time point can be the time point corresponding to the start of the next monitoring time point.

[0172] Based on the above technical solution, the optional, preset prediction model training process includes:

[0173] Acquire historical environmental data, historical load data, and historical speed errors at different monitoring time points, and create a first data set according to the monitoring time points, the historical environmental data, the historical load data, and the historical speed errors;

[0174] Constructing a prediction model, and training the prediction model according to the first data set until the prediction model reaches a preset prediction model training standard.

[0175] In this solution, historical environmental data may include external environmental conditions collected at different monitoring time points, such as temperature, humidity, pressure, etc.

[0176] The historical speed error may refer to a speed error record of the motor at different monitoring time points, indicating a difference between an actual speed and a target speed.

[0177] The monitoring time point refers to the specific time node for data collection, such as every minute, every hour, or other predetermined time intervals.

[0178] The first data set may be a data set including historical environmental data, historical load data, and historical speed errors, and is used to train a prediction model.

[0179] The preset training standard may refer to a standard used to determine the end of prediction model training, such as when the training error, accuracy, loss function value, etc. reaches a preset threshold.

[0180] Historical environmental data, historical load data, and historical speed errors at different monitoring time points can be collected. Specifically, these data can be extracted from existing data recording systems. The collected historical environmental data, historical load data, and historical speed errors are integrated according to the monitoring time points to form a data table. Select an appropriate prediction model type (such as linear regression, neural network, support vector machine, etc.). Divide the first data set into a training set and a test set (for example, 80% training, 20% testing). Use the training set to train the model and continuously adjust the model parameters. Use the test set to evaluate the model performance to ensure that the model is not overfitting or underfitting. You can set a preset prediction model training standard, such as the mean square error (MSE) is less than a certain value. Verify the model training results to ensure that the model meets the preset standards.

[0181] In this scheme, by training the prediction model, the future load and speed errors can be predicted more accurately.

[0182] S202: Calculate the predicted load membership of the predicted load data in each load range according to the predicted load data and a preset load membership calculation formula set.

[0183] The predicted load membership can indicate the membership degree of the predicted load data in each load range. This value is determined by calculating the predicted load data with a preset load membership calculation formula to determine its membership in different load ranges.

[0184] The predicted load data can be substituted into a preset load membership calculation formula set to obtain the predicted load membership of the predicted load data in each load range.

[0185] S203, calculating the predicted speed error membership of the predicted speed error in each speed error range according to the predicted speed error and a preset speed error membership calculation formula set.

[0186] The predicted speed error membership can indicate the membership degree of the predicted speed error in each speed error range. It determines its membership in different speed error ranges by calculating the predicted speed error with a preset speed error membership calculation formula.

[0187] The predicted speed error can be substituted into a preset speed error membership calculation formula set to obtain the predicted speed error membership of the predicted speed error in each speed error range.

[0188] S204, calculating the comprehensive predicted membership of each frequency adjustment rule in the frequency adjustment rule set according to the predicted load membership, the predicted speed error membership, the preset frequency adjustment rule set and the preset comprehensive membership calculation rule.

[0189] The comprehensive forecast membership can be used to calculate the forecast activation degree of each frequency adjustment rule. It combines the membership values ​​of the forecast load data and the forecast speed error data in each membership range, and determines the comprehensive membership of each rule through the preset frequency adjustment rule set and the comprehensive membership calculation rule.

[0190] The predicted load membership and the predicted speed error membership can be substituted into the preset comprehensive membership calculation rule to calculate the comprehensive predicted membership of each frequency adjustment rule in the frequency adjustment rule set.

[0191] S205, calculating a prediction frequency adjustment value according to the comprehensive prediction membership, the comprehensive adjustment frequency and a preset prediction frequency adjustment formula.

[0192] The predicted frequency adjustment value can be a predicted value calculated based on the comprehensive predicted membership and used to adjust the inverter output frequency. It is calculated by the fuzzy control system based on the predicted load data and predicted speed error data combined with the preset frequency adjustment rules to optimize the running state of the motor.

[0193] In this solution, the preset prediction frequency adjustment formula can be:

[0194]

[0195] Where FB is the predicted frequency adjustment value; u j is the comprehensive prediction membership of the jth frequency adjustment rule; j is the comprehensive adjustment frequency of the jth frequency adjustment rule; ∑ j (u j ·z j ) is the weighted sum of the comprehensive prediction membership of all frequency adjustment rules and the corresponding comprehensive adjustment frequency; ∑ j u j It is the sum of the comprehensive prediction membership of all frequency adjustment rules.

[0196] The comprehensive forecast membership and the comprehensive adjustment frequency can be substituted into a preset forecast frequency adjustment formula to calculate the forecast frequency adjustment value.

[0197] S206, before reaching the adjacent second monitoring time point, obtaining the second load data and the second speed error in real time, calculating the first load data change value of the first load data and the second load data, and calculating the first speed error change value of the first speed error and the second speed error.

[0198] The second monitoring time point may refer to the next monitoring time preset by the system after the first monitoring time point ends. This time point is the moment when the system performs the next inspection and adjustment on the motor running state.

[0199] The second load data is the motor load data collected in real time before reaching the second monitoring time point.

[0200] The second speed error is the motor speed error collected in real time before reaching the second monitoring time point, which represents the difference between the actual motor speed and the target speed.

[0201] The first load data change value may refer to the difference between the first load data and the second load data, which reflects the change trend of the load data.

[0202] The first speed error change value refers to the difference between the first load data and the second load data, which reflects the change trend of the speed error.

[0203] Before reaching the second monitoring time point, the second load data and the second speed error of the motor can be obtained through the real-time sensor. The first load data change value is calculated by the following formula:

[0204] First load data change value = | second load data - first load data |

[0205] The first speed error change value is calculated by the following formula:

[0206] First speed error change value = |second speed error - first speed error|

[0207] S207, obtaining a preset load weight, a preset speed error weight, a preset load weight calculation formula, and a preset speed error weight calculation formula, and calculating a first load weighted value of the first load data change value according to the first load data change value and the preset load weight calculation formula; wherein the preset load weight calculation formula is:

[0208] Load Weighted Value=PLW×LDVV;

[0209] Among them, Load Weighted Value is the load weighted value; PLW is the preset load weight; LDVV is the load data change value.

[0210] Preset load weights can refer to the weight values ​​set for load data in a fuzzy control system. These weights are used to determine the degree of impact of load changes on system control. The weight values ​​are usually set based on experience or system requirements to reflect the importance of load data in control decisions.

[0211] The preset speed error weight may refer to a weight value set for the speed error data in a fuzzy control system. These weights are used to determine the degree of influence of the speed error on the system control. The setting of the weight value is also based on experience or system requirements to reflect the importance of the speed error data in the control decision.

[0212] The preset load weight calculation formula may be a formula for calculating a weighted value of load data, which is based on a load change value and a preset load weight.

[0213] The preset speed error weight calculation formula may be a formula for calculating the speed error weight value, which is based on the speed error change value and the preset speed error weight.

[0214] The first load weighted value may be a value calculated based on the first load data change value and a preset load weight, and represents the weighted influence of the load change on the control decision.

[0215] The preset load weight, preset speed error weight, preset load weight calculation formula and preset speed error weight calculation formula can be read from the database, and the first load data change value is substituted into the "load data change value" of the formula to calculate the "first load weighted value" corresponding to the first load data change value.

[0216] S208, calculating a first speed error weighted value of the first speed error change value according to the first speed error change value and a preset speed error weight calculation formula; wherein the preset speed error weight calculation formula is:

[0217] Speed ​​Error Weighted Value=PSE*SEV;

[0218] Among them, Speed ​​Error Weighted Value is the speed error weighted value; PSE is the preset speed error; SEV is the speed error change value.

[0219] The first speed error weighted value can be substituted into the “speed error change value” of the formula to calculate its corresponding “first speed error weighted value”.

[0220] S209, obtaining a preset weighted sum calculation formula, and calculating a first weighted sum of the first load weighted value and the first speed error weighted value according to the first load weighted value, the first speed error weighted value and the preset weighted sum calculation formula; wherein the preset weighted sum calculation formula is:

[0221] Weighted Sum = LWV + SEWV;

[0222] Among them, Weighted Sum is the weighted sum; LWV is the load weighted value; SEWV is the speed error weighted value.

[0223] The preset weighted sum calculation formula may be a formula for comprehensively calculating the load weighted value and the speed error weighted value, and the formula is usually based on the sum of the weighted values.

[0224] The first weighted sum may be a comprehensive value calculated based on the first load weighted value and the first speed error weighted value by a preset weighted sum calculation formula, which represents the comprehensive impact of the load and speed error on the system control.

[0225] The first speed error change value can be substituted into the "speed error change value" of the formula, and the first load weighted value can be substituted into the "load weighted value" of the formula to obtain the corresponding "first weighted sum".

[0226] Based on the above technical solution, optionally, after calculating the first weighted sum of the first load weighted value and the first speed error weighted value, the method further includes:

[0227] If the first weighted sum does not exceed the preset weighted sum threshold before reaching the adjacent second monitoring time point, then when reaching the adjacent second monitoring time point, the third load data and the third speed error are obtained, and a second load data change value of the first load data and the third load data is calculated, and a second speed error change value of the first speed error and the third speed error is calculated;

[0228] Calculating a second load weighted value of the second load data change value according to the second load data change value and a preset load weight calculation formula;

[0229] Calculating a second speed error weighted value of the second speed error change value according to the second speed error change value and a preset speed error weight calculation formula;

[0230] Calculating a second weighted sum of the second load weighted value and the second speed error weighted value according to the second load weighted value, the second speed error weighted value and a preset weighted sum calculation formula;

[0231] If the second weighted sum exceeds a preset weighted sum threshold, the predicted frequency adjustment value is transmitted to the frequency converter, so that the frequency converter adjusts the output frequency according to the predicted frequency adjustment value.

[0232] In this solution, the third load data may be motor load data collected in real time at an adjacent second monitoring time point.

[0233] The third speed error may be a motor speed error acquired in real time at an adjacent second monitoring time point.

[0234] The second load data change value may be a difference between the first load data and the third load data.

[0235] The second speed error change value may be a difference between the first speed error and the third speed error.

[0236] The second load weighted value may be a weighted value calculated according to the second load data change value and a preset load weight calculation formula.

[0237] The second speed error weighted value may be a weighted value calculated according to the second speed error change value and a preset speed error weight calculation formula.

[0238] The second weighted sum may be the sum of the second load weighted value and the second speed error weighted value.

[0239] The third load data and the third speed error of the motor can be collected in real time at the adjacent second monitoring time point. The second load data change value is substituted into the "load data change value" of the formula to calculate the "first load weighted value" corresponding to the second load data change value. The second speed error weighted value is substituted into the "speed error change value" of the formula to calculate its corresponding "second speed error weighted value". The second speed error change value is substituted into the "speed error change value" of the formula, and the second load weighted value is substituted into the "load weighted value" of the formula to obtain its corresponding "second weighted sum". If the second weighted sum exceeds the preset weighted sum threshold, the predicted frequency adjustment value is transmitted to the frequency converter through wireless communication technology. The frequency converter adjusts the output frequency according to the predicted frequency adjustment value, thereby controlling the operating frequency of the motor.

[0240] In this solution, by real-time monitoring of changes in load and speed errors and making adjustments when the weighted sum exceeds the threshold, the actual working conditions can be more accurately reflected and the control accuracy can be improved. By accurately controlling the operating frequency of the motor, unnecessary energy consumption can be reduced, thereby achieving energy-saving effects.

[0241] Based on the above technical solution, optionally, after calculating the second weighted sum of the second load weighted value and the second speed error weighted value, the method further includes:

[0242] If the second weighted sum does not exceed a preset weighted sum threshold, the preset prediction model is retrained according to the third load data and the third speed error until the prediction model reaches a preset prediction model training standard.

[0243] In this solution, the new third load data and the third speed error can be added to the existing first data set to retrain the model. The prediction model is then retrained using the updated data set. During each training process, the model adjusts its parameters based on the new data to improve the prediction accuracy. After each training iteration, the performance of the model is evaluated to ensure that the prediction error of the model is gradually reduced until it reaches the preset training standard.

[0244] In this solution, real-time data collection and model retraining before the second monitoring time point is reached can improve the accuracy and adaptability of the prediction model. This process ensures that the prediction model always reflects the current system status and provides a more accurate frequency adjustment value for the inverter, thereby optimizing the operation and control of the motor.

[0245] S210: If the first weighted sum exceeds a preset weighted sum threshold before reaching an adjacent second monitoring time point, the predicted frequency adjustment value is transmitted to the frequency converter, so that the frequency converter adjusts the output frequency according to the predicted frequency adjustment value.

[0246] The preset weighted sum threshold is a set limit value used to determine whether the weighted sum exceeds the normal range. When the first weighted sum exceeds this threshold, the system will take corresponding measures.

[0247] If there is a first weighted sum that exceeds a preset weighted sum threshold before reaching an adjacent second monitoring time point, the predicted frequency adjustment value is immediately transmitted to the frequency converter via wireless transmission technology, and the frequency converter changes the output frequency according to this adjustment value, thereby controlling the operating frequency of the motor.

[0248] In this embodiment, prediction and adjustment are performed before adjacent monitoring time points, which can respond to possible changes in advance, reduce the impact of emergencies on the system, and improve the stability of the system. By acquiring the second load data and the second speed error in real time, the system can quickly respond to changes in the production process. This enables the system to adapt to different production conditions and environmental changes, and improves the adaptability and flexibility of the system.

[0249] Embodiment 3

[0250] Figure 3 is a flow chart of the inverter energy-saving control method provided in the third embodiment of the present application, such as Figure 3 As shown, the specific method includes the following steps:

[0251] S301, obtaining first load data and a first speed error of the motor at a first monitoring time point, and calculating the load membership of the first load data in each load range according to the first load data and a preset load membership calculation formula set.

[0252] S302: Calculate the speed error membership of the first speed error in each speed error range according to the first speed error and a preset speed error membership calculation formula set.

[0253] S303, obtaining a preset frequency adjustment rule set and a preset comprehensive membership calculation rule, and calculating the comprehensive membership of each frequency adjustment rule in the frequency adjustment rule set according to the load membership, the speed error membership, the preset frequency adjustment rule set and the preset comprehensive membership calculation rule.

[0254] S304, obtaining the comprehensive adjustment frequency of each frequency adjustment rule in the preset frequency adjustment rule set, calculating the frequency adjustment value according to the comprehensive membership, the comprehensive adjustment frequency and the preset frequency adjustment formula, and transmitting the frequency adjustment value to the frequency converter, so that the frequency converter adjusts the output frequency according to the frequency adjustment value, thereby controlling the operating frequency of the motor; wherein the preset frequency adjustment formula is:

[0255]

[0256] Among them, FA is the frequency adjustment value; u i is the comprehensive membership degree of the ith frequency adjustment rule; z i is the comprehensive adjustment frequency of the ith frequency adjustment rule; ∑ i (u i ·z i ) is the weighted sum of the comprehensive membership of all frequency adjustment rules and the corresponding comprehensive adjustment frequencies; ∑ i u i It is the sum of the comprehensive membership of all frequency adjustment rules.

[0257] S305, obtaining electrical parameters, mechanical parameters, environmental parameters, operating parameters and energy consumption parameters of the inverter, inputting the electrical parameters, mechanical parameters, environmental parameters, operating parameters and energy consumption parameters into a preset fault identification model to obtain a fault risk score, and determining whether the inverter has a fault risk based on the fault risk score and a preset risk score threshold.

[0258] The electrical parameters may be parameters related to the electrical performance of the inverter, for example, current, voltage, power factor, frequency, harmonic content, etc.

[0259] Mechanical parameters may be parameters related to the mechanical performance of the inverter and the motor, for example, bearing temperature, vibration, rotation speed, torque, etc.

[0260] Environmental parameters may be the conditions of the inverter working environment, for example, ambient temperature, humidity, dust concentration, vibration, etc.

[0261] The operating parameters may be parameters related to the frequency converter during operation, for example, operating time, number of starts, loading status, operating mode (such as constant speed operation, variable speed operation), etc.

[0262] The energy consumption parameters may be the energy consumption of the inverter and the motor, for example, power consumption, energy efficiency ratio, energy saving effect, etc.

[0263] The fault risk score can be a numerical value generated by the fault identification model to indicate the possibility or severity of a fault in the current operating state of the inverter. The score can be a continuous value ranging from 0 to 1 or from 0 to 100. The higher the score, the greater the possibility or severity of the fault.

[0264] The preset risk score threshold can be a fixed value, which is used to determine whether the fault risk score reaches or exceeds this value. When the fault risk score is higher than this threshold, the system will consider that the inverter has a fault risk. This threshold is set based on historical data and experience to ensure effective fault identification within a certain fault tolerance range.

[0265] The preset fault identification model can be a model trained by machine learning, neural networks, logical rules or other algorithms, which can predict whether the inverter has a fault risk based on input parameters and determine the cause of the fault.

[0266] Electrical, mechanical, environmental, operational and energy consumption parameters can be collected in real time from the sensors and monitoring systems of the inverter. The collected data is cleaned and preprocessed, including missing value processing, outlier detection and normalization. Ensure the integrity and consistency of the data to improve the accuracy of the model. The preprocessed data is input into the preset fault identification model. The model receives the input parameters and extracts useful features for analysis. Feature extraction can include statistical analysis of the data, trend analysis and calculation of specific indicators. The model calculates the health status and overall health score of each parameter based on the extracted features and the knowledge learned during training. For example, when using a neural network model, the input data is weighted by multiple neuron layers to output a fault risk score. If the fault risk score exceeds the preset risk score threshold, the inverter is considered to be at risk of failure.

[0267] Based on the above technical solution, the optional, preset fault identification model training process includes:

[0268] Acquire historical electrical parameters, historical mechanical parameters, historical environmental parameters, historical operating parameters, historical energy consumption parameters, and historical fault causes of the frequency converter, and create a second data set based on the historical electrical parameters, historical mechanical parameters, historical environmental parameters, historical operating parameters, historical energy consumption parameters, and historical fault causes;

[0269] A fault identification model is constructed, and the fault identification model is trained according to the second data set until the fault identification model reaches a preset fault identification model training standard.

[0270] In this solution, the historical electrical parameters can record the electrical status of the inverter, including current, voltage, power factor, etc.

[0271] Historical mechanical parameters can describe the mechanical state of the inverter drive, such as speed, vibration, torque, etc.

[0272] Historical environmental parameters can record the conditions of the environment in which the inverter is located, including temperature, humidity, etc.

[0273] The historical operating parameters can describe the operating status of the inverter, such as running time, operating mode, etc.

[0274] The historical energy consumption parameters can record the energy consumption information of the inverter, such as energy consumption, efficiency, etc.

[0275] The historical failure risk score is a numerical indicator that measures the failure risk of the inverter in historical data. It can be quantified based on factors such as the severity, frequency, and impact of the failure. The risk score is usually in the range of 0 to 1 or 0 to 100, where a high score indicates a higher failure risk and a low score indicates a lower failure risk.

[0276] The historical fault cause may be the specific cause of the inverter failure in the past, such as overcurrent, excessive bearing temperature, etc.

[0277] The second data set can be created from the above historical data, including all relevant parameters and fault causes at each time point. These data are used to train the fault identification model.

[0278] The historical electrical parameters, mechanical parameters, environmental parameters, operating parameters, energy consumption parameters and fault causes of the inverter can be obtained from the database, and then the data is cleaned to handle missing values ​​and outliers. Standardize or normalize the data to eliminate the influence of different parameter magnitudes, and integrate the above parameters and historical fault risk scores into a data set. Each row of data represents all parameters and corresponding risk scores at a time point. Create a second data set based on the preprocessed historical data for model training. Make sure that the data set includes samples of various types of faults and normal operation to ensure that the model can identify various situations. Then perform feature extraction on the second data set, which is the key to the performance of the machine learning model. The following feature extractions can be performed: Statistical analysis: Calculate the mean, variance, standard deviation and other statistics of each parameter. Trend analysis: Use methods such as sliding average and moving median to analyze the trend changes of parameters. Specific indicator calculation: Calculate specific health status indicators, such as total harmonic distortion of current, rate of change of bearing temperature, etc. Make sure that each data point in the second data set contains a label (fault cause and fault risk score), which will be used for supervised learning. Select an appropriate machine learning model, such as a neural network, decision tree, random forest, etc. Use the extracted features and historical fault causes as input for model training. During the training process, the model extracts features based on the input data and learns the relationship between these features and the fault risk score and fault cause. Use cross-validation and hyperparameter optimization to improve model performance. Train until the model reaches the preset fault identification model training standards (such as accuracy, recall, etc.).

[0279] In this solution, the training model can detect potential problems before failure occurs through real-time monitoring and fault identification, perform preventive maintenance, and avoid downtime caused by sudden equipment failure.

[0280] On the basis of the above technical solution, optionally, after building the fault identification model, training the fault identification model according to the second data set until the fault identification model reaches a preset fault identification model training standard, the method further includes:

[0281] If the preset model update time interval is reached, the historical electrical parameters, historical mechanical parameters, historical environmental parameters, historical operating parameters, historical energy consumption parameters, historical fault causes and historical fault risk scores of the inverter are collected again, and the second data set is updated. The fault identification model is retrained according to the updated second data set until the fault identification model meets the preset fault identification model training standard.

[0282] In this solution, the preset model update interval can be the cycle of model retraining and updating to ensure that the model maintains the latest status and accuracy. This interval can be set according to specific application requirements and system performance. Common intervals can be daily, weekly, monthly, etc.

[0283] The model update interval can be set according to system requirements and equipment operation. For example, the model can be updated once a month. Update the second data set based on the latest historical data collected, including removing noise data, processing missing values, and standardizing data formats. Integrate the newly collected data with the existing second data set to form a complete updated data set. Retrain the fault identification model based on the updated second data set, including extracting useful features from the data set, including statistical analysis, trend analysis, and calculation of specific indicators. Select a suitable model algorithm (such as neural network, decision tree, etc.). Input the extracted features into the model for training. Use the validation set to evaluate model performance and adjust model parameters to improve accuracy. Ensure that the model meets the preset fault identification model training standards, such as accuracy, recall, F1 score, etc. Deploy the updated model to the production environment to replace the old model.

[0284] In this solution, by regularly updating and retraining the fault identification model, it can be ensured that the model always remains accurate, timely reflects changes in equipment status, improves fault detection and prevention capabilities, and ensures system reliability and stability.

[0285] S306: If there is a fault risk, the fault cause is determined according to a preset fault identification model, and the fault cause is sent to the control center for the staff to troubleshoot and repair the fault according to the fault cause.

[0286] The cause of the fault can be a specific problem or parameter abnormality that causes the inverter to malfunction. For example, it can include overcurrent, overvoltage, bearing wear, high ambient temperature, excessive vibration, etc.

[0287] The control center can be a centralized management system responsible for monitoring and managing the operation of the inverter. It can receive fault alarms, analyze the causes of faults, develop maintenance plans, and perform necessary remote or on-site operations.

[0288] The model can receive real-time input of electrical parameters, mechanical parameters, environmental parameters, operating parameters, and energy consumption parameters. Extract features, including statistical analysis, trend analysis, and specific indicator calculations. The model calculates a fault risk score based on the extracted features. If the risk score exceeds a preset threshold, it is determined that there is a fault risk. The model then further analyzes the specific parameters and features that lead to a high risk score. For example, through a decision tree or neural network model, determine which parameter or feature leads to an abnormal score, and finally determine the cause of the fault, such as "overcurrent", "bearing temperature is too high", etc. The cause of the fault is then sent to the control center via the network or a dedicated communication system. After receiving the information, the control center notifies the relevant technicians for further analysis and processing.

[0289] In this embodiment, the fault response time can be shortened through automatic diagnosis and instant notification. Providing specific fault causes can help technicians quickly locate and repair problems, improve fault handling efficiency, and ensure stable operation of equipment.

[0290] Embodiment 4

[0291] Figure 4 is a structural diagram of a frequency converter energy-saving control system provided in Embodiment 4 of the present application, such as Figure 4 As shown, the system is used to implement a frequency converter energy-saving control system method provided in embodiments 1, 2, and 3, and the system specifically includes the following:

[0292] A load membership calculation module 401 is used to obtain first load data and a first speed error of the motor at a first monitoring time point, and calculate the load membership of the first load data in each load range according to the first load data and a preset load membership calculation formula set;

[0293] A speed error membership calculation module 402, configured to calculate the speed error membership of the first speed error in each speed error range according to the first speed error and a preset speed error membership calculation formula set;

[0294] The comprehensive membership calculation module 403 is used to obtain a preset frequency adjustment rule set, and calculate the comprehensive membership of each frequency adjustment rule in the frequency adjustment rule set according to the load membership, the speed error membership, the preset frequency adjustment rule set and the preset comprehensive membership calculation rule;

[0295] The output frequency adjustment module 404 is used to obtain the comprehensive adjustment frequency of each frequency adjustment rule in the preset frequency adjustment rule set, calculate the frequency adjustment value according to the comprehensive membership, the comprehensive adjustment frequency and the preset frequency adjustment formula, and transmit the frequency adjustment value to the inverter, so that the inverter adjusts the output frequency according to the frequency adjustment value, thereby controlling the operating frequency of the motor; wherein the preset frequency adjustment formula is:

[0296]

[0297] Among them, FA is the frequency adjustment value; u i is the comprehensive membership degree of the ith frequency adjustment rule; z i is the comprehensive adjustment frequency of the ith frequency adjustment rule; ∑ i (u i ·z i ) is the weighted sum of the comprehensive membership of all frequency adjustment rules and the corresponding comprehensive adjustment frequencies; ∑ i u i It is the sum of the comprehensive membership of all frequency adjustment rules.

[0298] In the embodiment of the present application, the load membership calculation module 401 is used to obtain the first load data and the first speed error of the motor at a first monitoring time point, and calculate the load membership of the first load data in each load range according to the first load data and a preset load membership calculation formula set; the speed error membership calculation module 402 is used to calculate the speed error membership of the first speed error in each speed error range according to the first speed error and a preset speed error membership calculation formula set; the comprehensive membership calculation module 403 is used to obtain a preset frequency adjustment rule set, and calculate the speed error membership of the first speed error in each speed error range according to the first speed error and a preset speed error membership calculation formula set; The output frequency adjustment module 404 is used to obtain the comprehensive adjustment frequency of each frequency adjustment rule in the preset frequency adjustment rule set, calculate the frequency adjustment value according to the comprehensive membership, the comprehensive adjustment frequency and the preset frequency adjustment formula, and transmit the frequency adjustment value to the frequency converter, so that the frequency converter adjusts the output frequency according to the frequency adjustment value, thereby controlling the running frequency of the motor; wherein the preset frequency adjustment formula is:

[0299]

[0300] Among them, FA is the frequency adjustment value; u i is the comprehensive membership degree of the ith frequency adjustment rule; z i is the comprehensive adjustment frequency of the ith frequency adjustment rule; ∑ i (ui ·z i ) is the weighted sum of the comprehensive membership of all frequency adjustment rules and the corresponding comprehensive adjustment frequencies; ∑ i u i It is the sum of the comprehensive membership of all frequency adjustment rules. Through the above inverter energy-saving control system, the operating frequency of the motor is adjusted according to the actual data of load and speed error, which avoids the motor running at an unnecessary high speed, thereby reducing energy waste and increasing the flexibility of adjustment. By calculating the comprehensive membership of load and speed error, the adjustment accuracy can be improved.

[0301] The above are only preferred embodiments of the present application and the technical principles used. The present application is not limited to the specific embodiments described herein, and various obvious changes, readjustments and substitutions that can be made by those skilled in the art will not deviate from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. A frequency converter energy-saving control method, characterized in that: The method comprises: Acquire first load data and a first speed error of the motor at a first monitoring time point, and calculate the load membership of the first load data in each load range according to the first load data and a preset load membership calculation formula set; Calculating the speed error membership of the first speed error in each speed error range according to the first speed error and a preset speed error membership calculation formula set; Obtaining a preset frequency adjustment rule set and a preset comprehensive membership calculation rule, and calculating the comprehensive membership of each frequency adjustment rule in the frequency adjustment rule set according to the load membership, the speed error membership, the preset frequency adjustment rule set and the preset comprehensive membership calculation rule; Obtain the comprehensive adjustment frequency of each frequency adjustment rule in the preset frequency adjustment rule set, calculate the frequency adjustment value according to the comprehensive membership, the comprehensive adjustment frequency and the preset frequency adjustment formula, and transmit the frequency adjustment value to the frequency converter, so that the frequency converter adjusts the output frequency according to the frequency adjustment value, thereby controlling the operating frequency of the motor; wherein the preset frequency adjustment formula is: ； Among them, FA is the frequency adjustment value; is the comprehensive membership degree of the ith frequency adjustment rule; is the comprehensive adjustment frequency of the ith frequency adjustment rule; is the weighted sum of the comprehensive membership of all frequency adjustment rules and the corresponding comprehensive adjustment frequencies; It is the sum of the comprehensive membership of all frequency adjustment rules.

2. The inverter energy-saving control method according to claim 1, characterized in that: After transmitting the frequency adjustment value to the frequency converter, the method further includes: Acquire current environmental data, input the first load data, the first speed error and the current environmental data into a preset prediction model to obtain predicted load data and predicted speed error; Calculating the predicted load membership of the predicted load data in each load range according to the predicted load data and a preset load membership calculation formula set; Calculating the predicted speed error membership of the predicted speed error in each speed error range according to the predicted speed error and a preset speed error membership calculation formula set; Calculate the comprehensive predicted membership of each frequency adjustment rule in the frequency adjustment rule set according to the predicted load membership, the predicted speed error membership, the preset frequency adjustment rule set and the preset comprehensive membership calculation rule; Calculating a prediction frequency adjustment value according to the comprehensive prediction membership, the comprehensive adjustment frequency and a preset prediction frequency adjustment formula; Before reaching an adjacent second monitoring time point, obtaining second load data and a second speed error in real time, calculating a first load data change value of the first load data and the second load data, and calculating a first speed error change value of the first speed error and the second speed error; Obtain a preset load weight, a preset speed error weight, a preset load weighted value calculation formula, and a preset speed error weighted value calculation formula, and calculate a first load weighted value of the first load data change value according to the first load data change value and the preset load weighted value calculation formula; wherein the preset load weighted value calculation formula is: ； in, is the load weighted value; is the preset load weight; is the load data change value; According to the first speed error change value and a preset speed error weighted value calculation formula, a first speed error weighted value of the first speed error change value is calculated; wherein the preset speed error weighted value calculation formula is: ； Among them, Speed ​​Error Weighted Value is the speed error weighted value; PSE is the preset speed error weight; SEV is the speed error change value; Obtain a preset weighted sum calculation formula, and calculate a first weighted sum of the first load weighted value and the first speed error weighted value according to the first load weighted value, the first speed error weighted value, and the preset weighted sum calculation formula; wherein the preset weighted sum calculation formula is: ； Among them, Weighted Sum is the weighted sum; is the load weighted value; is the speed error weighted value; If the first weighted sum exceeds a preset weighted sum threshold before reaching an adjacent second monitoring time point, the predicted frequency adjustment value is transmitted to the frequency converter so that the frequency converter adjusts the output frequency according to the predicted frequency adjustment value.

3. The inverter energy-saving control method according to claim 2, characterized in that: After calculating a first weighted sum of the first load weighted value and the first speed error weighted value, the method further includes: If the first weighted sum does not exceed the preset weighted sum threshold before reaching the adjacent second monitoring time point, then when reaching the adjacent second monitoring time point, the third load data and the third speed error are obtained, and a second load data change value of the first load data and the third load data is calculated, and a second speed error change value of the first speed error and the third speed error is calculated; Calculating a second load weighted value of the second load data change value according to the second load data change value and a preset load weight calculation formula; Calculating a second speed error weighted value of the second speed error change value according to the second speed error change value and a preset speed error weight calculation formula; Calculating a second weighted sum of the second load weighted value and the second speed error weighted value according to the second load weighted value, the second speed error weighted value and a preset weighted sum calculation formula; If the second weighted sum exceeds a preset weighted sum threshold, the predicted frequency adjustment value is transmitted to the frequency converter, so that the frequency converter adjusts the output frequency according to the predicted frequency adjustment value.

4. The inverter energy-saving control method according to claim 2, characterized in that: The training process of the preset prediction model includes: Acquire historical environmental data, historical load data, and historical speed errors at different monitoring time points, and create a first data set according to the monitoring time points, the historical environmental data, the historical load data, and the historical speed errors; Constructing a prediction model, and training the prediction model according to the first data set until the prediction model reaches a preset prediction model training standard.

5. The inverter energy-saving control method according to claim 3, characterized in that: After calculating the second weighted sum of the second load weighted value and the second speed error weighted value, the method further includes: If the second weighted sum does not exceed a preset weighted sum threshold, the preset prediction model is retrained according to the third load data and the third speed error until the prediction model reaches a preset prediction model training standard.

6. The inverter energy-saving control method according to claim 1, characterized in that: After transmitting the frequency adjustment value to the frequency converter, the method further includes: Obtaining electrical parameters, mechanical parameters, environmental parameters, operating parameters, and energy consumption parameters of the inverter, inputting the electrical parameters, mechanical parameters, environmental parameters, operating parameters, and energy consumption parameters into a preset fault identification model to obtain a fault risk score, and determining whether the inverter has a fault risk according to the fault risk score and a preset risk score threshold; If there is a risk of failure, the cause of the failure is determined based on a preset fault identification model, and the cause of the failure is sent to the control center for staff to troubleshoot and repair the failure based on the cause of the failure.

7. The inverter energy-saving control method according to claim 6, characterized in that: The training process of the preset fault identification model includes: Acquire historical electrical parameters, historical mechanical parameters, historical environmental parameters, historical operating parameters, historical energy consumption parameters, historical fault causes, and historical fault risk scores of the frequency converter, and create a second data set based on the historical electrical parameters, historical mechanical parameters, historical environmental parameters, historical operating parameters, historical energy consumption parameters, historical fault causes, and historical fault risk scores; A fault identification model is constructed, and the fault identification model is trained according to the second data set until the fault identification model reaches a preset fault identification model training standard.

8. The inverter energy-saving control method according to claim 7, characterized in that: After constructing the fault identification model and training the fault identification model according to the second data set until the fault identification model reaches a preset fault identification model training standard, the method further includes: If the preset model update time interval is reached, the historical electrical parameters, historical mechanical parameters, historical environmental parameters, historical operating parameters, historical energy consumption parameters, historical fault causes and historical fault risk scores of the inverter are collected again, and the second data set is updated. The fault identification model is retrained according to the updated second data set until the fault identification model meets the preset fault identification model training standard.

9. The inverter energy-saving control method according to claim 1, characterized in that: The preset load membership calculation formula set includes: Low load membership formula: ； in, is the load membership of the load data in the low-load fuzzy set; is the load data; is the low load membership of the load data in the low load set. The lower the load, the higher the low load membership. Ensure that the load membership is within the range of [0, 1] and cannot be lower than 0 or higher than 1; and when the load data is lower than 5, the load membership is 1; Medium load membership formula: ； in, is the load membership of the load data in the medium load fuzzy set; is the load data; is the medium load membership of the load data in the medium load interval. The closer the load data is to 5, the higher the medium load membership is. The medium load membership degree is calculated for another part of the load data in the medium load interval. The closer the load data is to 10, the higher the medium load membership degree is. Ensure that the load membership is within the range of [0, 1] and the load membership cannot be lower than 0 or higher than 1; High load membership formula: ； in, is the load membership of the load data in the high-load fuzzy set; is the load data; is the high load membership of the load data in the high load interval. The higher the load data, the higher the high load membership. Ensure that the load membership is in the range of [0, 1] and cannot be lower than 0 or higher than 1; and the maximum value of the high load membership in the high load interval is 1. When the load data is lower than 5, the high load membership is 0.

10. A frequency converter energy-saving control system, characterized in that: The system comprises: A load membership calculation module, used to obtain first load data and a first speed error of the motor at a first monitoring time point, and calculate the load membership of the first load data in each load range according to the first load data and a preset load membership calculation formula set; A speed error membership calculation module, used to calculate the speed error membership of the first speed error in each speed error range according to the first speed error and a preset speed error membership calculation formula set; A comprehensive membership calculation module, used to obtain a preset frequency adjustment rule set, and calculate the comprehensive membership of each frequency adjustment rule in the frequency adjustment rule set according to the load membership, the speed error membership, the preset frequency adjustment rule set and the preset comprehensive membership calculation rule; The output frequency adjustment module is used to obtain the comprehensive adjustment frequency of each frequency adjustment rule in the preset frequency adjustment rule set, calculate the frequency adjustment value according to the comprehensive membership, the comprehensive adjustment frequency and the preset frequency adjustment formula, and transmit the frequency adjustment value to the frequency converter, so that the frequency converter adjusts the output frequency according to the frequency adjustment value, thereby controlling the operating frequency of the motor; wherein the preset frequency adjustment formula is: ； Among them, FA is the frequency adjustment value; is the comprehensive membership degree of the ith frequency adjustment rule; is the comprehensive adjustment frequency of the ith frequency adjustment rule; is the weighted sum of the comprehensive membership of all frequency adjustment rules and the corresponding comprehensive adjustment frequencies; It is the sum of the comprehensive membership of all frequency adjustment rules.

Images