Electromagnetic wire intelligent production full-process management and control system for new energy equipment

Abstract

The invention discloses an electromagnetic wire intelligent production full-process management and control system for new energy equipment, and belongs to the technical field of production management and control, and the system comprises a data collection module which is used for collecting related data of winding equipment during flat wire winding, and the related data comprises tension change, position deviation and speed in the winding process; the data processing module is used for adjusting related data according to the normal tension, position and speed of the winding equipment when the flat wire is wound, and the adjusting mode comprises adjusting operation parameters of the winding equipment through a control algorithm; and the data fusion analysis module is used for analyzing the regular change of the related data according to the normal tension, position and speed of the winding equipment when the flat wire is wound. According to the invention, comprehensive and intelligent management and control of the electromagnetic wire winding process of the new energy equipment are realized, the production efficiency is improved, and the stability and reliability of production are enhanced.

Description

Technical Field

[0001] This invention relates to the field of production control technology, and in particular to an intelligent full-process control system for the production of electromagnetic wires for new energy equipment. Background Technology

[0002] Magnet wire is an insulated wire used to manufacture coils or windings in electrical products.

[0003] With the rapid development of the new energy industry, higher requirements have been placed on the quality and production efficiency of electromagnetic wires in new energy equipment. Traditional electromagnetic wire production processes have many problems; quality control mainly relies on manual inspection, which is inefficient and prone to errors, making it difficult to meet the high precision and high reliability requirements of new energy equipment for electromagnetic wires.

[0004] Regarding this research, application CN202211075443.8 provides a control method and system for new energy vehicle parts production equipment. This technical solution includes: acquiring registered production equipment; determining a workshop model based on the production equipment; receiving a product index input by a user; querying the production process; determining control parameters containing time information for each production piece of equipment based on the production process; acquiring the operating parameters of the production equipment in real time; determining the anomaly level of each production piece of equipment; and correcting the control parameters of each production piece of equipment based on the anomaly level. This technical solution determines the control parameters of each production piece of equipment based on the production process, and then workers can make time-based fine adjustments to the determined control parameters according to the production progress, thus conveniently determining the control parameters of each production piece of equipment and reducing workload to a certain extent.

[0005] Another application, CN202111085771.1, provides a holographic digital intelligent equipment monitoring system for new energy power plants. This technical solution includes a physical unit, a data unit, a service unit, and an application unit. The physical unit establishes a holographic model of the new energy power plant equipment and transmits operational data to the data unit in real time. The data unit collects and processes monitoring data from the physical unit. The service unit performs data governance on the data from the data unit and achieves real-time operational data perception and analysis. This technical solution enables a realistic display of important facilities and equipment, IoT data acquisition devices, and equipment in the computer room of the new energy power plant, and overlays operational status information, achieving operational supervision, equipment operation monitoring, and automatic process control of power facilities.

[0006] The aforementioned technical solutions are all used for the control and management of a specific piece of equipment during production and / or use. However, these solutions still suffer from poor precision in controlling complex processes. For the control of some complex electromagnetic wire production processes, such as the winding and insulation coating of flat wire in flat wire motors, existing control systems struggle to achieve high-precision control. Taking the entire flat wire winding process as an example, the requirements for precise control of winding tension and position are extremely high to ensure accurate number of turns and good interlayer insulation, thereby guaranteeing the performance and reliability of the motor. Existing systems cannot fully meet these high-precision control requirements, easily leading to quality problems such as turn errors and interlayer short circuits, which in turn affect the performance and reliability of the product. Summary of the Invention

[0007] In view of the problems existing in the field of production control technology, the present invention is proposed.

[0008] Therefore, one of the objectives of this invention is to provide an intelligent full-process control system for the production of electromagnetic wires for new energy equipment. Through the collaborative work of multiple modules such as data fusion analysis, adaptive control, machine learning algorithms, regular change calculation, and reference parameter groups, it achieves comprehensive and intelligent control over the electromagnetic wire winding process of new energy equipment, thereby improving production efficiency and enhancing production stability and reliability.

[0009] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0010] This invention provides a smart production process control system for electromagnetic wires in new energy equipment, comprising:

[0011] The data acquisition module is used to collect relevant data of the winding equipment during the winding of flat wire, including tension changes, position deviations and speeds during the winding process;

[0012] The data processing module is used to adjust the relevant data based on the normal tension, position and speed of the winding equipment when winding flat wire. The adjustment method includes adjusting the operating parameters of the winding equipment through a control algorithm.

[0013] The data fusion analysis module is used to analyze the regular changes of the relevant data based on the normal tension, position and speed of the winding equipment when winding flat wire. The data fusion analysis module includes an acquisition unit, an analysis unit, a calculation unit and a judgment unit.

[0014] The acquisition unit is used to acquire the tension change, position deviation and speed corresponding to the error in the number of turns of the flat wire when the winding equipment made a historical winding of the flat wire, and to mark the tension change, position deviation and speed as a risk parameter group;

[0015] The analysis unit responds to the risk parameter set to analyze the tension changes, position deviations, and speeds before the risk parameter set appears, and provides an analysis interval based on the tension changes, position deviations, and speeds.

[0016] The calculation unit response analysis unit is used to divide the analysis interval into a type A data analysis interval, a type B data analysis interval, and a type C data analysis interval; and to calculate the differences between the tension change, position deviation, and velocity and the risk parameter group in each type of data analysis interval; and to mark the three differences as a risk difference group.

[0017] Among the various data analysis intervals, the tension change, position deviation, and speed corresponding to the C-type data analysis interval are closest to the risk parameter group, followed by the tension change, position deviation, and speed corresponding to the B-type data analysis interval, and then the tension change, position deviation, and speed corresponding to the A-type data analysis interval.

[0018] In a preferred embodiment of the present invention, the judgment unit responds to the calculated difference and calculates the difference with the risk parameter group based on relevant data collected in the future time period, and compares the calculated difference with the risk difference group. If the calculated difference is the same as any one of the differences in the risk difference group or is between the three differences in the risk difference group, the system determines that there will be a turn error in the flat wire winding and adjusts the operating parameters of the winding equipment through the control algorithm; otherwise, no adjustment is made.

[0019] In a preferred embodiment of the present invention, the operating parameters of the winding equipment are adjusted by a control algorithm, including adjusting the operating parameters according to adaptive control, as shown below:

[0020] T(k+1)=aT(k)+b△T(k);

[0021] P(k+1)=cP(k)+d△P(k);

[0022] Where T(k) and P(k) are the tension and position deviation at time k, respectively, ΔT(k) and ΔP(k) are the tension and position adjustment at time k, respectively, and a, b, c, and d represent the dynamic parameters of the winding equipment.

[0023] In a preferred embodiment of the present invention, the method further includes adjusting the operating parameters according to a machine learning algorithm. The machine learning algorithm includes a neural network model, in which the adjustment amount Δθ of the operating parameters is used as the output, and the current operating state x of the winding equipment and the process parameter y are used as inputs, as shown below:

[0024] △θ=f NN (x, y·w);

[0025] In the formula, Δθ represents the adjustment amount of the operating parameters, which is the adjustment amount of the operating parameters predicted by the neural network model, f NN Let w represent the parameters of the neural network model;

[0026] Among them, the operating status x includes the tension, speed and position deviation of the winding equipment; the process parameter y includes the winding speed and temperature.

[0027] In a preferred embodiment of the present invention, the following steps are taken: characteristic changes of tension, position and velocity are obtained in the A-type data analysis interval, the B-type data analysis interval and the C-type data analysis interval; normal values ​​and abnormal values ​​of tension, position and velocity are collected in the characteristic changes; the proportion of tension, position and velocity in each of the data analysis intervals is calculated based on the abnormal values; and the regular changes of the remaining objects are calculated based on the object with the largest proportion.

[0028] In a preferred embodiment of the present invention, the regular changes of the remaining objects are calculated based on the object with the largest proportion, and the result is obtained according to the following formula:

[0029] V = k T ·T+b T ; where k T It is the proportionality coefficient, b T It is a constant term;

[0030] In the formula, V represents the winding speed, T represents the winding tension, and k T This indicates the degree to which tension changes affect velocity; if k T >0 indicates that the velocity increases with increasing tension; if k T <0 indicates that the speed decreases as the tension increases;

[0031] b T This represents the velocity offset when the tension is 0.

[0032] In a preferred embodiment of the present invention, the calculation of the regular changes of the remaining objects based on the object with the largest proportion further includes calculating according to the following formula:

[0033] P = k P ·T+b P ; where k P It is the proportionality coefficient, b P It is a constant term;

[0034] In the formula, P represents the positional deviation, T represents the winding tension, and k P This indicates the degree to which tension changes affect positional deviation. If k PIf k > 0, it means that the positional deviation increases as the tension increases; if k P <0 indicates that the positional deviation decreases when the tension increases;

[0035] b P This represents the positional deviation when the tension is 0.

[0036] In a preferred embodiment of the present invention, the adjustment range of the operating parameters is determined based on the calculated regular changes, and the operating parameters are divided into [variables] within the adjustment range. Parameter group Parameter group and The parameter set is used to obtain the correlation between different parameter sets and the tension, position, and velocity in the outlier, and the correlation includes the time it takes for the tension, position, and velocity in the outlier to return to the normal value.

[0037] In a preferred embodiment of the present invention, the tension, position, and speed are sorted according to the duration of the time taken, and the parameter group that can restore a certain object to its normal value first is obtained from the sorted objects. The parameter group is marked as the reference parameter group. If the tension, position, and speed are in an abnormal state in the future, the operating parameters are adjusted based on the reference parameter group.

[0038] Beneficial effects:

[0039] 1. The data acquisition module acquires real-time data on tension changes, position deviations, and speed during the winding process, and adjusts the data based on normal parameters. This allows for timely correction of deviations in the production process, reducing the defect rate caused by abnormal parameters and thus improving production efficiency. Furthermore, the adaptive control algorithm adjusts the operating parameters of the winding equipment, dynamically optimizing the equipment's operating status based on real-time monitoring data. This ensures the equipment operates at its optimal working point, further enhancing production efficiency.

[0040] 2. Machine learning algorithms (such as neural network models) adjust operating parameters. The system can learn patterns from a large amount of historical data, predict and optimize equipment operating parameters to adapt to complex production environments and dynamically changing process requirements, realize intelligent production, and further improve production efficiency.

[0041] 3. This invention can calculate risk difference groups based on historical data and real-time monitoring data, and provide early warnings of risks that may occur in the future. Once a difference similar to the risk parameter group is detected, the system will adjust the operating parameters in a timely manner to prevent quality problems from occurring, thereby improving product quality.

[0042] 4. Based on the calculated patterns of change, determine the adjustment range for operating parameters, and within the adjustment range, obtain the correlation between different parameter groups and abnormal values. This allows us to find a reference parameter group that can restore the parameters to normal values ​​most quickly. In future abnormal situations, adjusting the operating parameters based on the reference parameter group can quickly restore the normal state of the production process and reduce the occurrence of quality problems. Attached Figure Description

[0043] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0044] Figure 1 This is a schematic diagram of the modular structure of the intelligent production process control system for electromagnetic wires in new energy equipment according to an embodiment of the present invention.

[0045] Figure 2 This is a schematic diagram of the process structure of an embodiment of the present invention;

[0046] The diagram is labeled as follows: 110 - Data acquisition module; 120 - Data processing module; 130 - Data fusion and analysis module; 1301 - Acquisition unit; 1302 - Analysis unit; 1303 - Calculation unit; 1304 - Judgment unit. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention are within the scope of protection of the present invention.

[0048] Because existing technologies cannot fully meet the requirements for such high-precision control, quality problems such as turns error and inter-layer short circuits are prone to occur, which in turn affect the performance and reliability of the product.

[0049] Based on this, the present invention proposes an intelligent full-process control system for the production of electromagnetic wires for new energy equipment. Through the collaborative work of multiple modules such as data fusion analysis, adaptive control, machine learning algorithms, regular change calculation, and reference parameter groups, it realizes comprehensive and intelligent control over the electromagnetic wire winding process of new energy equipment, improves production efficiency, and enhances the stability and reliability of production.

[0050] The present solution will be further described in detail below through embodiments and in conjunction with the accompanying drawings.

[0051] Reference Figures 1 to 2 As one embodiment of the present invention, this embodiment provides a smart production process control system for electromagnetic wires in new energy equipment, comprising:

[0052] The data acquisition module 110 is used to collect relevant data of the winding equipment during the winding of flat wire, including tension changes, position deviations and speeds during the winding process;

[0053] In this embodiment, in one feasible implementation, high-precision sensors, including tension sensors, position sensors, and speed sensors, are installed at key locations of the flat wire winding equipment. The tension sensor is used to monitor the tension changes of the flat wire in real time during the winding process; the position sensor accurately measures the position deviation of the flat wire during the winding process; and the speed sensor monitors whether the winding speed is uniform.

[0054] The data processing module 120 is used to adjust relevant data based on the normal tension, position and speed of the winding equipment when winding flat wire. The adjustment method includes adjusting the operating parameters of the winding equipment through a control algorithm.

[0055] In this embodiment, the operating parameters include temperature, winding angle, and winding pressure;

[0056] The data fusion analysis module 130 is used to analyze the regular changes of relevant data based on the normal tension, position and speed of the winding equipment when winding flat wire. The data fusion analysis module 130 includes an acquisition unit 1301, an analysis unit 1302, a calculation unit 1303 and a judgment unit 1304.

[0057] The acquisition unit 1301 is used to acquire the tension change, position deviation and speed corresponding to the error in the number of turns of the flat wire when the winding equipment made a historical winding of the flat wire, and to mark the tension change, position deviation and speed as a risk parameter group;

[0058] Analysis unit 1302 responds to the risk parameter set, which is used to analyze the tension changes, position deviations and velocities before the occurrence of the risk parameter set, and to give the analysis interval based on the tension changes, position deviations and velocities;

[0059] The calculation unit 1303 is a response analysis unit, used to divide the analysis interval into Class A data analysis interval, Class B data analysis interval and Class C data analysis interval; and to calculate the differences between tension change, position deviation and velocity and risk parameter group in each type of data analysis interval; and to mark the three differences as risk difference group.

[0060] Among the various data analysis intervals, the tension change, position deviation, and speed corresponding to the C-type data analysis interval are closest to the risk parameter group, followed by the tension change, position deviation, and speed corresponding to the B-type data analysis interval, and then the tension change, position deviation, and speed corresponding to the A-type data analysis interval.

[0061] The judgment unit 1304 responds to the calculated difference value, which is used to calculate the difference with the risk parameter group based on the relevant data collected in the future time period, and compares the calculated difference value with the risk difference value group. If the calculated difference value is the same as any difference value in the risk difference value group or is between the three differences in the risk difference value group, the system determines that there will be a turn error in the flat wire winding, and adjusts the operating parameters of the winding equipment through the control algorithm; otherwise, no adjustment is made.

[0062] In this embodiment, through the collaborative work of the acquisition unit, analysis unit, calculation unit and judgment unit, the system can analyze historical data, identify risk parameter groups related to turns error, and provide early warning of potential future risks.

[0063] Furthermore, this application not only focuses on the change of a single parameter, but also comprehensively considers the interrelationship between multiple parameters, providing a comprehensive analytical perspective;

[0064] The operating parameters of the winding equipment are adjusted through control algorithms, including adjustments based on adaptive control, as shown below:

[0065] T(k+1)=aT(k)+b△T(k);

[0066] P(k+1)=cP(k)+d△P(k);

[0067] Where T(k) and P(k) are the tension and position deviation at time k, respectively, ΔT(k) and ΔP(k) are the tension and position adjustment at time k, respectively, and a, b, c, and d represent the dynamic parameters of the winding equipment.

[0068] In this embodiment, adaptive control is a control method that can automatically adjust the control strategy according to the changes in the dynamic characteristics of the system. During the flat wire winding process of the flat wire motor, the winding tension, position and other parameters are affected by a variety of factors and have certain dynamic changes. Therefore, the adaptive control algorithm can effectively adjust the operating parameters of the winding equipment in real time.

[0069] In this embodiment, the adaptive control algorithm can dynamically adjust the operating parameters of the winding equipment based on real-time monitoring data, so that the equipment operates at the optimal operating point.

[0070] Furthermore, this embodiment also includes adjusting the operating parameters according to a machine learning algorithm. The machine learning algorithm includes a neural network model, in which the adjustment amount of the operating parameters Δθ is used as the output, and the current operating state x of the winding equipment and the process parameter y are used as the input, as shown below:

[0071] △θ=f NN (x, y·w);

[0072] In the formula, Δθ represents the adjustment amount of the operating parameters, which is the adjustment amount of the operating parameters predicted by the neural network model, and f NN represents the neural network model, and w represents the parameters of the neural network model;

[0073] Among them, the operating status x includes the tension, speed and position deviation of the winding equipment; the process parameter y includes the winding speed and temperature;

[0074] In this embodiment, during the flat wire winding process of the flat wire motor, precise control of the operating parameters of the winding equipment is crucial to ensuring product quality. Machine learning algorithms can learn patterns from a large amount of historical data, predict and optimize equipment operating parameters to adapt to complex production environments and dynamically changing process requirements. This article will introduce a parameter adjustment method based on machine learning algorithms, which aims to improve the stability of the winding process and product quality.

[0075] In this embodiment, by utilizing a neural network model, the system can learn patterns from a large amount of historical data, predict and optimize equipment operating parameters, achieve intelligent decision-making, and the intelligent parameter adjustment can quickly adapt to production changes, further improving production efficiency.

[0076] Based on the above, the characteristic changes of tension, position and velocity are obtained in the A-type data analysis interval, the B-type data analysis interval and the C-type data analysis interval. Normal values ​​and abnormal values ​​of tension, position and velocity are collected in the characteristic changes. The proportion of tension, position and velocity in each data analysis interval is calculated based on the abnormal values. The regular changes of the remaining objects are calculated based on the object with the largest proportion.

[0077] In this embodiment, the system can identify characteristic changes in tension, position, and velocity, and collect normal and abnormal values, providing data support for subsequent analysis of regular changes;

[0078] By calculating the proportion of each parameter in different data analysis intervals, the system can determine the parameter with the largest proportion, providing a basis for calculating regular changes.

[0079] It is important to emphasize in this embodiment that the regular changes of the remaining objects are calculated based on the object with the largest proportion, using the following formula:

[0080] V = k T ·T+b T ; where k T It is the proportionality coefficient, b T It is a constant term;

[0081] In the formula, V represents the winding speed, T represents the winding tension, and k T This indicates the degree to which tension changes affect velocity; if k T >0 indicates that the velocity increases with increasing tension; if k T <0 indicates that the speed decreases as the tension increases;

[0082] b T This represents the velocity offset when the tension is 0.

[0083] In this embodiment, tension, speed and position deviation are three important parameters that are related to each other in the winding equipment. By analyzing the variation law of one of the parameters, the variation law of the other two parameters can be derived.

[0084] In this embodiment, the system can accurately calculate the effect of tension changes on speed, providing a clear direction for adjustment;

[0085] Based on real-time data, the system can dynamically adjust the speed to adapt to changes in tension;

[0086] Specifically, this embodiment calculates the regular changes of the remaining objects based on the object with the largest proportion, and also includes calculations based on the following formula:

[0087] P = k P ·T+b P ; where k P It is the proportionality coefficient, b P It is a constant term;

[0088] In the formula, P represents the positional deviation, T represents the winding tension, and k P This indicates the degree to which tension changes affect positional deviation. If k P If k > 0, it means that the positional deviation increases as the tension increases; if k P <0 indicates that the positional deviation decreases when the tension increases;

[0089] b P This represents the positional deviation when the tension is 0.

[0090] In this embodiment, the system can accurately calculate the impact of tension changes on position deviation. Based on real-time data, the system can dynamically adjust the position deviation to adapt to changes in tension.

[0091] It should be noted that the adjustment range for the operating parameters is determined based on the calculated pattern of change. Within this adjustment range, the operating parameters are divided into... Parameter group Parameter group and The parameter set obtains the correlation between different parameter sets and the tension, position, and velocity in outliers. The correlation includes the time it takes for the tension, position, and velocity in outliers to return to normal values.

[0092] In this embodiment, the system determines the adjustment range based on the regular changes and divides the operating parameters into different parameter groups, providing a refined adjustment strategy;

[0093] A refined adjustment strategy can quickly restore the production process to normal and reduce the time spent handling anomalies;

[0094] Furthermore, the tension, position, and speed are sorted according to the duration of time. From the sorted objects, the parameter group that can restore a certain object to its normal value first is selected and marked as the reference parameter group. If the tension, position, and speed are in abnormal value in the future, the operating parameters are adjusted based on the reference parameter group.

[0095] In this embodiment, the system can find a reference parameter group that can restore a certain parameter to its normal value the fastest, providing the optimal adjustment scheme for future abnormal situations;

[0096] Rapid response and optimal adjustment solutions can reduce production downtime and improve production efficiency.

[0097] In summary, this application achieves comprehensive and intelligent control over the electromagnetic wire winding process of new energy equipment through the collaborative work of multiple modules such as data fusion analysis, adaptive control, machine learning algorithms, regular change calculation, and reference parameter groups, thereby improving production efficiency and enhancing production stability and reliability.

[0098] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A smart production process control system for electromagnetic wires in new energy equipment, characterized in that, include: The data acquisition module is used to collect relevant data of the winding equipment during the winding of flat wire, including tension changes, position deviations and speeds during the winding process; The data processing module is used to adjust the relevant data based on the normal tension, position and speed of the winding equipment when winding flat wire. The adjustment method includes adjusting the operating parameters of the winding equipment through a control algorithm. The data fusion analysis module is used to analyze the regular changes of the relevant data based on the normal tension, position and speed of the winding equipment when winding flat wire. The data fusion analysis module includes an acquisition unit, an analysis unit, a calculation unit and a judgment unit. The acquisition unit is used to acquire the tension change, position deviation and speed corresponding to the error in the number of turns of the flat wire when the winding equipment made a historical winding of the flat wire, and to mark the tension change, position deviation and speed as a risk parameter group; The analysis unit responds to the risk parameter set to analyze the tension changes, position deviations, and speeds before the risk parameter set appears, and provides an analysis interval based on the tension changes, position deviations, and speeds. The calculation unit responds to the analysis unit, which is used to divide the analysis interval into a type A data analysis interval, a type B data analysis interval, and a type C data analysis interval. The differences between the tension change, position deviation, and velocity and the risk parameter group are calculated in various data analysis intervals; the three differences are marked as risk difference groups. Among the various data analysis intervals, the tension change, position deviation, and speed corresponding to the C-type data analysis interval are closest to the risk parameter group, followed by the tension change, position deviation, and speed corresponding to the B-type data analysis interval, and then the tension change, position deviation, and speed corresponding to the A-type data analysis interval.

2. The intelligent full-process control system for electromagnetic wire production in new energy equipment as described in claim 1, characterized in that, The judgment unit responds to the calculated difference value, which is used to calculate the difference with the risk parameter group based on the relevant data collected in the future time period, and compares the calculated difference value with the risk difference value group. If the calculated difference value is the same as any difference value in the risk difference value group or is between the three differences in the risk difference value group, the system determines that there will be a turn error in the flat wire winding, and adjusts the operating parameters of the winding equipment through the control algorithm; otherwise, no adjustment is made.

3. The intelligent full-process control system for electromagnetic wire production in new energy equipment as described in claim 2, characterized in that, The operating parameters of the winding equipment are adjusted through control algorithms, including adjustments based on adaptive control, as shown below: T(k+1)=aT(k)+b△T(k); P(k+1)=cP(k)+d△P(k); Where T(k) and P(k) are the tension and position deviation at time k, respectively, ΔT(k) and ΔP(k) are the tension and position adjustment at time k, respectively, and a, b, c, and d represent the dynamic parameters of the winding equipment.

4. The intelligent full-process control system for electromagnetic wire production in new energy equipment as described in claim 3, characterized in that, It also includes adjusting operating parameters based on a machine learning algorithm, which includes a neural network model. In the neural network model, the adjustment amount of the operating parameters Δθ is used as the output, and the current operating state x of the winding equipment and the process parameter y are used as the input, as shown below: △θ=f NN (x,y·w); In the formula, Δθ represents the adjustment amount of the operating parameters, which is the adjustment amount of the operating parameters predicted by the neural network model, f NN Let w represent the parameters of the neural network model; Among them, the operating status x includes the tension, speed and position deviation of the winding equipment; the process parameter y includes the winding speed and temperature.

5. The intelligent full-process control system for electromagnetic wire production in new energy equipment as described in claim 1, characterized in that, The characteristic changes of tension, position and velocity are obtained in the A-type data analysis interval, the B-type data analysis interval and the C-type data analysis interval. Normal values ​​and abnormal values ​​of tension, position and velocity are collected in the characteristic changes. The proportion of tension, position and velocity in each of the data analysis intervals is calculated based on the abnormal values. The regular changes of the remaining objects are calculated based on the object with the largest proportion.

6. The intelligent full-process control system for electromagnetic wire production in new energy equipment as described in claim 5, characterized in that, The regular changes of the remaining objects are calculated based on the object with the largest proportion, using the following formula: V = k T ·T+b T ; where k T It is the proportionality coefficient, b T It is a constant term; In the formula, V represents the winding speed, T represents the winding tension, and k T This indicates the degree to which tension changes affect velocity; if k T >0 indicates that the velocity increases with increasing tension; if k T <0 indicates that the speed decreases as the tension increases; b T This represents the velocity offset when the tension is 0.

7. The intelligent full-process control system for electromagnetic wire production in new energy equipment as described in claim 6, characterized in that, The calculation of the regular changes in the remaining objects is based on the object with the largest proportion, and also includes calculations based on the following formula: P = k P ·T+b P ; where k P It is the proportionality coefficient, b P It is a constant term; In the formula, P represents the positional deviation, T represents the winding tension, and k P This indicates the degree to which tension changes affect positional deviation. If k P If k > 0, it means that the positional deviation increases as the tension increases; if k P <0 indicates that the positional deviation decreases when the tension increases; b P This represents the positional deviation when the tension is 0.

8. A smart production process control system for electromagnetic wires in new energy equipment as described in claims 6-7, characterized in that, Based on the calculated regular changes, the adjustment range for the operating parameters is determined. Within the adjustment range, the operating parameters are divided into... Parameter group Parameter group and The parameter set is used to obtain the correlation between different parameter sets and the tension, position, and velocity in the outlier, and the correlation includes the time it takes for the tension, position, and velocity in the outlier to return to the normal value.

9. The intelligent full-process control system for electromagnetic wire production in new energy equipment as described in claim 8, characterized in that, Based on the duration of the time taken, the tension, position, and speed are sorted. From the sorted objects, the parameter group that can restore a certain object to its normal value first is selected and marked as the reference parameter group. If the tension, position, and speed are in an abnormal state in the future, the operating parameters are adjusted based on the reference parameter group.

Images