Soft start device multi-parameter cooperative control system based on intelligent sensing

Abstract

The invention provides a soft start device multi-parameter cooperative control system based on intelligent sensing, and relates to the technical field of multi-parameter cooperation, and the control system comprises a multi-data collection module which is used for collecting various data. And the self-assembly fusion strategy module is used for setting starting parameters according to the motor state data, fusing various parameter data to obtain multi-parameter fusion data, and analyzing the multi-parameter fusion data to obtain a control strategy. And the parameter adjustment balance module is used for extracting abnormal working condition processing data from the historical working condition data and adjusting the control strategy according to the abnormal working condition processing data to obtain a balance control instruction. And the parameter stable start control module is used for adjusting the start initial data according to the start parameter to obtain a device start parameter, and controlling multiple parameters of the soft start device according to the balance control instruction. According to the method, the control instruction is balanced, so that the system can quickly take treatment measures when an accident occurs, the risk of equipment damage is reduced, and the response capability of the system to abnormal working conditions and the fault treatment efficiency are enhanced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of multi-parameter coordination, in particular to a multi-parameter coordination control system for soft start device based on intelligent sensing. BACKGROUND

[0002] In modern industrial production, as a key equipment for motor starting, the performance of soft start device directly affects the starting effect of motor and the stable operation of equipment. With the continuous improvement of industrial automation, the requirements for intelligentization and multi-parameter coordination control of soft start device are increasing.

[0003] The soft start device in the prior art has many defects. First, in terms of starting parameter setting, the traditional soft start device often sets the starting parameters according to experience or fixed parameter setting mode. However, the load type of motor is various, and the running situation is complex and changeable. This non-targeted starting parameter setting method leads to unreasonable starting parameters.

[0004] Secondly, the soft start device generates various parameter data during operation, such as voltage, current, frequency, motor speed, temperature, etc. These data reflect the running state of the soft start device and motor, but the fusion of various data in the prior art is difficult. On the one hand, there is a complex relationship and mutual influence between different types of data, which is difficult to accurately correlate and analyze; on the other hand, due to the limitations of data acquisition and processing technology, it is difficult to effectively integrate and mine a large amount of multi-source heterogeneous data. This makes it impossible to fully utilize the information contained in these data, and further affects the comprehensive understanding and accurate control of the running state of the soft start device.

[0005] In addition, when the soft start device appears abnormal working condition, the prior art does not handle the abnormal working condition in time. Abnormal working conditions may include overload, short circuit, overvoltage, undervoltage and other conditions. The traditional soft start device often lacks effective abnormal working condition monitoring and processing mechanism. When abnormal working condition occurs, the abnormal signal cannot be detected in time and accurately, and reasonable processing measures cannot be taken quickly, which may cause the equipment to run continuously in abnormal state, resulting in equipment damage and even safety accidents.

[0006] In order to solve the problems of unreasonable starting parameter setting, difficult fusion of various data and untimely handling of abnormal working condition of soft start device in the prior art, a multi-parameter coordination control system for soft start device based on intelligent sensing is needed. SUMMARY

[0007] The present application provides a multi-parameter coordination control system for soft start device based on intelligent sensing, which solves the defects of unreasonable starting parameter setting, difficult fusion of various data and untimely handling of abnormal working condition of soft start device in the prior art.

[0008] The application provides a soft start device multi-parameter collaborative control system based on intelligent sensing, comprising: A multi-data collection module is configured to collect initial start data in real time, collect multi-parameter data and motor state data of the soft start device according to a preset time interval, and collect historical working condition data.

[0009] A self-organizing strategy module is configured to set a start parameter according to the motor state data, fuse the multi-parameter data according to a rough set theory method to obtain multi-parameter fusion data, and analyze the multi-parameter fusion data using a self-organizing mapping algorithm to obtain a control strategy.

[0010] A parameter balance module is configured to extract abnormal working condition processing data from the historical working condition data according to a parameter variation control method, and adjust the control strategy according to the abnormal working condition processing data to obtain a balance control instruction.

[0011] A parameter stability start control module is configured to adjust the initial start data according to the start parameter to obtain a device start parameter, and control the multi-parameters of the soft start device according to the balance control instruction.

[0012] The soft start device multi-parameter collaborative control system based on intelligent sensing comprises the following steps: The load characteristics are obtained according to the load type and load operation condition of the motor, and the start mode is determined in combination with the load type.

[0013] The load characteristics are converted into a characteristic curve, and the starting voltage is set in combination with the load operation condition.

[0014] The ramp time is set according to the load operation condition and the preset start speed, and the current limiting multiple is set according to the starting voltage and the load operation condition.

[0015] The soft start device multi-parameter collaborative control system based on intelligent sensing comprises the following steps of fusing the multi-parameter fusion data: The multi-parameter data are subjected to data cleaning and normalization processing, and are organized in the form of an information table, with each row representing an operating state and each column representing a parameter data, and a decision attribute is defined.

[0016] The dependency of each decision attribute is calculated, and it is judged whether the dependency decreases when a parameter data is deleted, and if yes, the current parameter data is retained, and if not, the current parameter data is deleted.

[0017] For the retained parameter data, different equivalence classes are divided according to the similarity of attribute values, and the lower approximation set and the upper approximation set of each decision attribute are calculated.

[0018] Multiple lower approximation sets and upper approximation sets are divided into different equivalence classes and then fused to obtain multi-parameter fused data.

[0019] The steps for analyzing and obtaining the control strategy in the multi-parameter collaborative control system for a soft-start device based on intelligent sensing provided by the present invention include: The data range in the multi-parameter fused data is mapped to the same interval to obtain the mapping result, and missing values ​​and outliers are removed.

[0020] The topology of the self-organizing map algorithm is determined, and the weight vector of each neuron is randomly initialized so that the number of neurons is consistent with the number of parameters in the multi-parameter fusion data.

[0021] The Mahalanobis distance is used to calculate the distance between each parameter and the weight vectors of all neurons. The neuron with the smallest distance is selected as the best matching unit, and the weight vectors of the best matching unit and its neighbors are updated.

[0022] When the change in the weight vector is less than a preset threshold, the distance calculation stops, and cluster analysis is performed on the multi-parameter fusion data based on the weight vector distribution and mapping of each neuron to obtain different clusters.

[0023] The characteristics and patterns of each cluster are analyzed to obtain the features of multi-parameter fusion data under different operating conditions. Corresponding control instructions are formulated based on different clusters and features, and multiple control instructions are integrated to obtain a control strategy.

[0024] The steps for obtaining the optimal matching unit in the multi-parameter collaborative control system for a soft-start device based on intelligent sensing provided by the present invention include: Calculate the covariance matrix of multi-parameter fused data.

[0025] Mahalanobis distance is used to calculate the distance between each parameter and the weight vector of each neuron.

[0026] The neuron with the smallest distance among the multiple distances obtained is the best matching unit.

[0027] The multi-parameter collaborative control system for a soft-start device based on intelligent sensing provided by this invention updates the weight vectors of the best matching unit and neurons in the neighborhood, as expressed by the following formula:

[0028] In the formula, It is the updated weight vector. During training time At that time, in the self-organizing map algorithm, the first... Line number The weight vector of the neurons in the column. It's the learning rate. is a field function, is a dataset of multi-parameter fusion data.

[0029] According to the soft start device multi-parameter collaborative control system based on intelligent sensing provided by the application, the step of extracting abnormal working condition processing data comprises: According to the technical specifications and operation requirements of the soft start device, the standard of abnormal working condition is defined, and the standard is adjusted according to the changes of multiple parameter data to obtain the abnormal working condition standard.

[0030] According to the abnormal working condition standard, the time series analysis method is used to dynamically analyze the historical working condition data, and the time period in which the parameter change trend does not conform to the normal operation mode is identified.

[0031] The types and processing measures of the abnormal working conditions corresponding to multiple time periods are classified and arranged to obtain abnormal working condition processing data.

[0032] According to the soft start device multi-parameter collaborative control system based on intelligent sensing provided by the application, the step of adjusting to obtain the balance control instruction comprises: The abnormal condition processing data is classified according to the abnormal type, processing measure and occurrence time, and the key features are extracted therefrom.

[0033] The effectiveness of the control strategy in handling abnormal working conditions is analyzed, and the association model between the key features and the control strategy is established based on the variational method, and the adjustment strategy adopted in different key feature abnormal working conditions is determined.

[0034] According to the adjustment strategy, the control strategy is coordinated and balanced under the abnormal working condition generated under different key features and the preset abnormal condition, and the balance control instruction is obtained.

[0035] According to the soft start device multi-parameter collaborative control system based on intelligent sensing provided by the application, the step of obtaining the adjustment strategy comprises: For each type of abnormal working condition, the effectiveness level of the control strategy adopted in the current abnormal working condition is analyzed from the aspects of abnormal elimination time, equipment damage degree, control stability and energy consumption.

[0036] According to the effectiveness level and the key features, the target functional is constructed, and the constraint condition is defined.

[0037] The variational operation is performed on the target functional, the extreme value under the constraint condition is solved, the characteristic strategy equation is obtained, and the relationship between the key features and the control strategy is solved to establish the association model.

[0038] For abnormal working conditions with different key feature combinations, the current key features are input into the association model, and the processing scheme for the current abnormal working condition is calculated.

[0039] According to the difference between the current multiple processing schemes and control strategies, the adjustment direction and content are adjusted to obtain the adjustment strategy.

[0040] According to the application, the soft starting device multi-parameter collaborative control system based on intelligent sensing is provided, and the step of adjusting the device starting parameter comprises: The internal relationship between the starting parameter and the starting initial data is analyzed, and the influence of the load inertia on the starting is comprehensively obtained to obtain the correlation relationship.

[0041] It is judged whether the starting initial data is in the preset range, if yes, no adjustment is needed, otherwise, the starting initial data is adjusted according to the correlation relationship to obtain the starting data.

[0042] A plurality of process indicators when using the starting data are monitored, and abnormal conditions are summarized to obtain abnormal data.

[0043] The starting data is adjusted according to the abnormal data to obtain the device starting parameter.

[0044] The soft starting device multi-parameter collaborative control system based on intelligent sensing is provided, and the starting parameter and the starting data are reasonably set, so that the soft starting device can start according to the actual situation of the motor and the load, the problems of starting failure, equipment damage or energy waste caused by improper starting parameter are solved, the stability and reliability of the equipment starting are improved, and the service life of the equipment is prolonged. Through the fusion processing of a plurality of parameter data, the system can more comprehensively and accurately understand the running state of the soft starting device, the problems of complicated parameter data and unclear correlation between parameters are solved, and the data processing and analysis ability of the system is improved.

[0045] The soft starting device multi-parameter collaborative control system based on intelligent sensing is provided, and the control strategy is formulated to better cope with different running states and abnormal working conditions, improve the control precision and response speed of the system, realize the collaborative control of the multi-parameter of the soft starting device, and optimize the overall performance of the system.

[0046] The soft starting device multi-parameter collaborative control system based on intelligent sensing is provided, and the balance control instruction is formulated, so that the system can quickly respond when the abnormal working condition occurs, take effective processing measures, reduce the risk of equipment damage, and enhance the response ability and fault processing efficiency of the system to abnormal working conditions. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings described below are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0048] Fig. 1 is one of the process schematic diagrams of the soft start device multi-parameter collaborative control system based on intelligent sensing provided by the embodiments of the present application. Fig. 2 is the second process schematic diagram of the soft start device multi-parameter collaborative control system based on intelligent sensing provided by the embodiments of the present application. Fig. 3 is the third process schematic diagram of the soft start device multi-parameter collaborative control system based on intelligent sensing provided by the embodiments of the present application. DETAILED DESCRIPTION

[0049] In order to make the objects, technical solutions and advantages of the present application clearer, the following will combine the drawings in the present application to clearly and completely describe the technical solutions in the present application. Obviously, the described embodiments are some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0050] The following will combine Figs. 1-3 to describe the soft start device multi-parameter collaborative control system based on intelligent sensing of the present application.

[0051] As shown in Figs. 1-3 , the soft start device multi-parameter collaborative control system based on intelligent sensing provided by the embodiments of the present application comprises: A multi-data collection module is used to collect real-time initial data of starting, collect various parameter data and motor state data of the soft start device according to preset time intervals, and collect historical working condition data.

[0052] The initial data of starting refers to the real-time state data of the equipment and load collected before the soft start device starts, such as the initial temperature of the motor, the winding resistance, the inertia moment of the load, the initial rotating speed, etc. These data can be collected by means of temperature sensors, rotating speed sensors, etc. and monitoring systems.

[0053] The various state data of the motor are collected by intelligent sensors, including but not limited to rated voltage, rated current, rated power, winding temperature, ambient temperature, motor rotating speed, etc. Various parameter data involved in the running process of the soft start device are also collected, such as current, voltage, temperature, rotating speed, torque, etc.

[0054] Collect historical operating data generated during the operation of the soft starter, including but not limited to parameters such as motor current, voltage, speed, torque, and temperature, as well as control parameters and operating status information of the soft starter. This data may come from smart sensors, data recording devices, or monitoring systems.

[0055] The self-organizing fusion module is used to set starting parameters based on motor status data, fuse multiple parameter data according to rough set theory to obtain multi-parameter fusion data, and use self-organizing mapping algorithm to analyze and obtain control strategy.

[0056] The steps to set startup parameters include: Based on the motor's load type and operating conditions, the load characteristics are obtained, and the starting mode is determined in conjunction with the load type. For fan and pump loads, a ramp constant current soft start method is selected. For heavy-load applications requiring overcoming significant static friction, a pulse impact start method can be used.

[0057] Convert the load characteristics into a characteristic curve and set the starting voltage based on the load operating conditions. The starting voltage should be set between 30% and 60% of the rated voltage. If the motor cannot start or starts too slowly, the initial voltage can be increased appropriately, but not exceeding 50% of the rated voltage; otherwise, the motor may be subjected to starting torque shock, which could damage mechanical parts.

[0058] Set the ramp time based on the load conditions and preset start-up speed, and set the current limiting factor based on the starting voltage and load conditions. Lighter loads require shorter start-up times, while heavier loads require longer start-up times. If the motor can start successfully but the start-up time is too long, the ramp time can be appropriately shortened. Conversely, if there is a large current surge during startup, the ramp time can be extended.

[0059] The steps to obtain multi-parameter fused data include: Data from various parameters is cleaned and normalized, and then organized into an information table. Each row represents the running status, each column represents a parameter, and decision attributes are defined.

[0060] Calculate the dependency of each decision attribute. Based on the dependency, determine whether deleting a parameter data point will decrease the current parameter data. If so, retain the current parameter data; otherwise, delete the current parameter data.

[0061] For the retained parameter data, it is divided into different equivalence classes based on the similarity of attribute values, and the lower approximation set and upper approximation set of each decision attribute are calculated.

[0062] Multiple lower approximation sets and upper approximation sets are divided into different equivalence classes and then fused to obtain multi-parameter fused data.

[0063] The steps to analyze and derive the control strategy include: The mapping results are obtained by mapping the data range in the multi-parameter fused data to the same interval, and missing values ​​and outliers are removed.

[0064] The topology of the self-organizing map algorithm is determined, and the weight vector of each neuron is randomly initialized so that the number of neurons is consistent with the number of parameters in the multi-parameter fusion data.

[0065] Mahalanobis distance is used to calculate the distance between each parameter and the weight vectors of all neurons, and the neuron with the smallest distance is selected as the best matching unit.

[0066] The steps to obtain the best matching unit include: The covariance matrix of multi-parameter fused data is calculated using the following formula:

[0067] In the formula, It is a dataset of multi-parameter fusion data. It is sample data. It is the covariance matrix. It is a dataset The mean vector, It is transpose.

[0068] Mahalanobis distance is used to calculate the distance between each parameter and the weight vector of each neuron. The formula is as follows:

[0069] In the formula, It is the number of parameters. In the self-organizing map algorithm, the first Line number The weight vector of the neurons in the column. It is the inverse of the covariance matrix. It's distance.

[0070] The neuron with the smallest distance among the multiple distances obtained is the best matching unit.

[0071] The weight vectors of the best-matching unit and its neighbors are updated using the following formula:

[0072] In the formula, It is the updated weight vector. During training time At that time, in the self-organizing map algorithm, the first... Line number The weight vector of the neurons in the column. It's the learning rate. is a field function, is a dataset of multi-parameter fusion data.

[0073] When the change of the weight vector is less than a preset threshold, the distance is stopped to be calculated, and the multi-parameter fusion data is analyzed for clustering according to the weight vector distribution and mapping of each neuron, to obtain different clusters.

[0074] The characteristics and modes of each cluster are analyzed to obtain the characteristics of the multi-parameter fusion data under different operating states, and corresponding control instructions are formulated according to different clusters and characteristics, and the control strategy is obtained by integrating the control instructions.

[0075] The reference balance module is used to extract abnormal working condition processing data from historical working condition data according to the reference variable control analysis method, and adjust the control strategy to obtain a balanced control instruction.

[0076] The steps of extracting abnormal working condition processing data include: The standard of abnormal working condition is defined according to the technical specifications and operating requirements of the soft start device, and the standard is adjusted according to the changes of multiple parameter data to obtain the abnormal working condition standard.

[0077] According to the abnormal working condition standard, a time series analysis method is used to dynamically analyze the historical working condition data, and the time period in which the parameter change trend does not conform to the normal operation mode is identified. The predicted value of each time point is calculated. The actual measured value is compared with the predicted value, and when the deviation between the two exceeds a preset threshold, it is considered that the time point may be abnormal. By continuously monitoring the deviation of multiple time points, the time period in which the parameter change trend does not conform to the normal operation mode is identified. For each abnormal working condition, the treatment measures taken at the time of the occurrence of the working condition are recorded. The treatment measures can include automatic control actions taken by the soft start device (such as adjusting voltage, current limit, shutdown, etc.), and manual intervention measures (such as adjusting parameter settings, restarting the device, etc.). These treatment measures are classified in different ways, such as automatic control and manual control, or according to the specific type of treatment measures (such as voltage adjustment, current limit, etc.). The types of abnormal working conditions and the corresponding treatment measures are integrated to form abnormal working condition processing data. Tables, databases, etc. can be used to store and manage these data for subsequent query and analysis.

[0078] The types and treatment measures of the abnormal working conditions corresponding to the multiple time periods are classified and arranged to obtain abnormal working condition processing data. The abnormal working condition types can include overload, overvoltage, undervoltage, overheating, startup failure, etc.

[0079] The steps of adjusting the balanced control instruction include: Abnormal operating condition handling data is categorized according to abnormality type, handling measures, and occurrence time, and key features are extracted from these categories. Handling measures may include adjusting voltage, current limiting, and shutdown. Key features may include parameter values ​​at the time of the abnormality (such as the specific values ​​of current and voltage), the duration of the abnormality, and the response time of the handling measures.

[0080] The effectiveness of control strategies under each abnormal operating condition is analyzed, and a correlation model between key features and control strategies is established based on variational method to determine the adjustment strategies to be adopted under abnormal operating conditions with different key features.

[0081] The steps to obtain the adjustment strategy include: For each type of abnormal operating condition, the effectiveness level of the control strategy adopted under the current abnormal operating condition is analyzed from the aspects of abnormal elimination time, equipment damage degree, control stability and energy consumption.

[0082] Based on the effectiveness level and key characteristics, an objective functional is constructed, and constraints are defined according to the physical characteristics, operating limitations, and actual working conditions of the soft-start device.

[0083] Variational operations are performed on the objective functional to solve for the extreme values ​​under constraints, thereby obtaining the characteristic policy equation. The relationship between key features and control policies is then obtained by solving the equation, and a correlation model is established.

[0084] For abnormal operating conditions with different combinations of key features, the current key features are input into the correlation model to calculate the processing solution for the current abnormal operating condition.

[0085] Based on the differences between the current processing schemes and control strategies, the direction and content of the adjustments are clarified to obtain the adjustment strategy. The adjustment strategy may include precise adjustment of control parameters (such as fine-tuning the values ​​of parameters such as starting voltage and current limiting factor) and optimization of the sequence of control actions (changing the order of control actions or adding new control links).

[0086] Under abnormal operating conditions and preset abnormal conditions arising from different key characteristics, the control strategy is coordinated and balanced according to the adjustment strategy to obtain a balanced control command. For example, when overload and overheating anomalies occur simultaneously, the control strategy must consider both reducing the load to solve the overload problem and taking measures to dissipate heat to deal with the overheating problem, and the operations of the two must not conflict with each other. The balanced control command clearly specifies how the various actuators (such as thyristors, contactors, etc.) of the soft starter should operate under different abnormal operating conditions, and how the relevant parameters should be adjusted.

[0087] The parameter stabilization and start-up control module is used to adjust the initial start-up data according to the start-up parameters to obtain the device start-up parameters.

[0088] The step of adjusting the device start-up parameters comprises: The internal relationship between the start-up parameters and the start-up initial data is analyzed, and the influence of the load inertia on the start-up is comprehensively considered to obtain the correlation.

[0089] It is judged whether the start-up initial data is within the preset range. If yes, no adjustment is needed. Otherwise, the start-up initial data is adjusted according to the correlation to obtain the start-up data. The method of adjusting the start-up initial data according to the correlation can comprise: when the motor temperature is high, the starting voltage can be increased by 5%-10% on the basis of the original starting voltage to compensate for the influence of the increased resistance and ensure sufficient start-up current. When the load inertia is large, the ramp time is extended by 20%-50%, and the torque boost value is increased by 10%-20% to meet the demand of load start-up.

[0090] A plurality of process indicators when using the start-up data are monitored, and abnormal conditions are summarized to obtain abnormal data. The process indicators can include start-up current, motor speed, torque change, etc. The abnormal conditions can include unstable motor start-up, abnormal vibration, noise, etc.

[0091] The start-up data is adjusted according to the abnormal data to obtain the device start-up parameters.

[0092] The plurality of parameters of the soft start device are controlled according to the balance control instruction. According to the setting of the key parameters such as starting voltage, ramp time, current limiting multiple, torque boost value in the balance control instruction, the real-time monitoring of the parameter change of the soft start device in the start-up process is carried out. When it is detected that the start-up current exceeds the reasonable range set by the instruction, the current limiting multiple is adjusted in time to ensure that the current is stable in the safe and effective range. If the motor speed does not rise according to the expected ramp time or fluctuates, the ramp time and torque boost value are fine-tuned according to the instruction to ensure that the motor can smoothly and efficiently reach the rated speed. At the same time, the torque change of the motor is continuously monitored, and the torque boost value is flexibly adjusted in combination with the actual situation of the load to avoid start-up failure due to insufficient torque or damage to the equipment due to excessive torque.

[0093] The soft start device multi-parameter collaborative control system based on intelligent sensing provided by the embodiment avoids the problems of start failure, equipment damage or energy waste caused by improper start parameters by determining the load characteristics and start mode according to the load type and operation condition of the motor, and then converting the load characteristics and start mode into a characteristic curve to set the starting voltage, and setting the ramp time, current limiting multiple and the like in combination with the operation condition and preset speed. The stability and reliability of the equipment start are improved, and the service life of the equipment is prolonged. The fusion processing of various parameter data is also performed, so that the system can more comprehensively and accurately understand the operation state of the soft start device. The self-organizing mapping algorithm is used to process the multi-parameter fusion data, and the control strategy is analyzed and obtained, so that the blindness and irrationality of the previous control strategy formulation are changed. The time series analysis method is also used to identify the abnormal time period, the data of the abnormal working condition is classified and analyzed, the correlation model is determined based on the variational method, the balanced control instruction is obtained through the coordinated balance control strategy, the problems of untimely and inaccurate abnormal working condition processing and the control strategy unable to effectively respond to the abnormality are solved, the risk of equipment damage is reduced, and the response capability and fault processing efficiency of the system to the abnormal working condition are enhanced. At the same time, the reasonable start parameter setting and the optimized control strategy avoid unnecessary energy consumption, improve the energy utilization efficiency, and meet the requirements of energy saving and environmental protection. The system can comprehensively consider various factors, adapt to different types of motors and loads and complex and changeable operation conditions, has strong universality and adaptability, and can meet the needs of different users.

[0094] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and necessary general hardware platforms, and of course, can also be realized by hardware. Based on such understanding, the above technical solutions or the essential part of the prior art can be embodied in the form of a software product, which can be stored in a computer readable storage medium such as ROM / RAM, magnetic disk, optical disk and the like, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the method described in each embodiment or some parts of the embodiment.

[0095] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to some technical features thereof; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A multi-parameter collaborative control system for a soft-start device based on intelligent sensing, characterized in that, include: The multi-data collection module is used to collect initial startup data in real time, collect various parameter data and motor status data of the soft starter at preset time intervals, and collect historical operating condition data. The self-organizing fusion module is used to set starting parameters based on the motor state data, fuse multiple parameter data according to rough set theory to obtain multi-parameter fusion data, and analyze it using the self-organizing mapping algorithm to obtain the control strategy. The parameter adjustment and balancing module is used to extract abnormal operating condition processing data from the historical operating condition data according to the parameter variable control analysis method, and adjust the control strategy according to the abnormal operating condition processing data to obtain a balancing control command. The parameter stabilization and start-up control module is used to adjust the initial start-up data according to the start-up parameters to obtain the device start-up parameters, and to control multiple parameters of the soft-start device according to the balance control command.

2. The multi-parameter collaborative control system for a soft-start device based on intelligent sensing according to claim 1, characterized in that, The steps for setting the startup parameters include: Based on the motor's load type and operating conditions, the load characteristics are obtained, and the starting mode is determined in conjunction with the load type. The load characteristics are converted into characteristic curves, and the starting voltage is set in conjunction with the load operating conditions; The ramp time is set according to the load operation and the preset start-up speed, and the current limiting factor is set according to the starting voltage and the load operation.

3. The multi-parameter collaborative control system for a soft-start device based on intelligent sensing according to claim 1, characterized in that, The steps to obtain multi-parameter fused data include: Multiple parameter data are cleaned and normalized, and then organized into an information table. Each row represents the running status, each column represents a parameter data, and decision attributes are defined. Calculate the dependency of each decision attribute, and determine whether the current parameter data decreases when a parameter data is deleted based on the dependency. If so, retain the current parameter data; otherwise, delete the current parameter data. For the retained parameter data, it is divided into different equivalence classes based on the similarity of attribute values, and the lower approximation set and upper approximation set of each decision attribute are calculated. The multi-parameter fused data is obtained by dividing multiple lower approximation sets and upper approximation sets into different equivalence classes and fusing them.

4. The multi-parameter collaborative control system for a soft-start device based on intelligent sensing according to claim 1, characterized in that, The steps for analyzing and obtaining the control strategy include: The data ranges in the multi-parameter fused data are mapped to the same interval to obtain the mapping results, and missing values ​​and outliers are removed; The topology of the self-organizing map algorithm is determined, and the weight vector of each neuron is randomly initialized so that the number of neurons is consistent with the number of parameters in the multi-parameter fusion data. The Mahalanobis distance is used to calculate the distance between each parameter and the weight vectors of all neurons, and the neuron with the smallest distance is selected as the best matching unit. The weight vectors of the best matching unit and the neurons in its neighborhood are then updated. When the change in the weight vector is less than a preset threshold, the distance calculation stops, and cluster analysis is performed on the multi-parameter fusion data based on the weight vector distribution of each neuron and the mapping to obtain different clusters; The characteristics and patterns of each cluster are analyzed to obtain the features of the multi-parameter fusion data under different operating states. Corresponding control instructions are formulated based on different clusters and features, and multiple control instructions are integrated to obtain the control strategy.

5. The multi-parameter collaborative control system for a soft-start device based on intelligent sensing according to claim 4, characterized in that, The steps to obtain the optimal matching unit include: Calculate the covariance matrix of the multi-parameter fused data; The Mahalanobis distance is used to calculate the distance between each parameter and the weight vector of each neuron; The neuron with the smallest distance from the obtained multiple distances is the optimal matching unit.

6. The multi-parameter collaborative control system for a soft-start device based on intelligent sensing according to claim 4, characterized in that, The weight vectors of the best-matching unit and the neurons in its neighborhood are updated using the following formula: ； In the formula, It is the updated weight vector. During training time At that time, in the self-organizing map algorithm, the first... Line 1 The weight vector of the neurons in the column. It's the learning rate. It is a domain function. It is a dataset of multi-parameter fusion data.

7. The multi-parameter collaborative control system for a soft-start device based on intelligent sensing according to claim 1, characterized in that, The steps for extracting the abnormal operating condition processing data include: The abnormal operating condition standard is defined based on the technical specifications and operating requirements of the soft starter, and the standard is adjusted by taking into account the changes in multiple parameter data to obtain the abnormal operating condition standard. Based on the abnormal operating condition standard, a time series analysis method is used to dynamically analyze the historical operating condition data and identify the time periods in which the parameter change trend does not conform to the normal operating mode. The abnormal operating conditions and their handling measures corresponding to multiple time periods are classified and organized to obtain the abnormal operating condition handling data.

8. The multi-parameter collaborative control system for a soft-start device based on intelligent sensing according to claim 1, characterized in that, The steps for obtaining the balance control command include: The abnormal operating condition processing data is classified according to the abnormality type, processing measures, and occurrence time, and key features are extracted from them; The effectiveness of the control strategy under each abnormal operating condition is analyzed, and a correlation model between the key features and the control strategy is established based on the variational method to determine the adjustment strategy to be adopted under abnormal operating conditions with different key features. Under abnormal operating conditions and preset abnormal conditions generated under different key characteristics, the control strategy is coordinated and balanced according to the adjustment strategy to obtain the balanced control command.

9. The multi-parameter collaborative control system for a soft-start device based on intelligent sensing according to claim 8, characterized in that, The steps to obtain the adjustment strategy include: For each type of abnormal operating condition, the effectiveness level of the control strategy adopted under the current abnormal operating condition is analyzed from the aspects of abnormal elimination time, equipment damage degree, control stability and energy consumption. Based on the effectiveness level and the key features, construct the objective functional and define the constraints. Variational operations are performed on the objective functional to solve for the extreme values ​​under the constraints, thereby obtaining the characteristic policy equation. The relationship between the key features and the control policy is then obtained by solving the equation, and the correlation model is established. For abnormal operating conditions with different combinations of key features, the current key features are input into the association model to calculate the processing solution for the current abnormal operating condition. Based on the differences between the current multiple processing schemes and the control strategy, the adjustment direction and content are determined to obtain the adjustment strategy.

10. The multi-parameter collaborative control system for a soft-start device based on intelligent sensing according to claim 1, characterized in that, The steps for adjusting and obtaining the device startup parameters include: The inherent relationship between the startup parameters and the initial startup data is analyzed, and the correlation is obtained by taking into account the influence of load inertia on startup. Determine whether the initial startup data is within a preset range. If it is, no adjustment is needed; otherwise, adjust the initial startup data according to the correlation to obtain the startup data. Multiple process metrics are monitored when the startup data is used, and abnormal situations are summarized to obtain abnormal data; The device startup parameters are obtained by adjusting the startup data based on the abnormal data.

Images