Screw processing machine control system based on end-cloud collaboration

Abstract

The invention relates to the technical field of industrial control, and discloses a control system of a screw processing machine table based on terminal cloud collaboration. Comprising a parameter acquisition module which is used for splicing a control period and acquiring real-time processing parameters; the model identification module is used for identifying standard processing parameters through a deep learning model; the control analysis module is used for drawing a stable curve graph and judging whether a cooperative control mode is executed or not; the cooperative control module is used for performing cooperative control operation on the screw processing machine table; according to the invention, by splicing the control period with the period units distributed at intervals, the evaluation process of thread rolling processing of the screw processing machine can be divided at intervals and circularly, and reasonable redundant buffer time is reserved for data transmission and interaction between the mechanical end and the cloud end; the interaction of data between the mechanical end and the cloud end is improved, the phenomena of data discretization and confusion are avoided, and safety guarantee is provided for end-cloud cooperative control.

Description

Technical Field

[0001] This invention relates to the field of industrial control technology, and more specifically, to a control system for a screw processing machine based on end-to-end cloud collaboration. Background Technology

[0002] With the advancement of intelligent manufacturing and industrial digitalization, the control technology of screw processing machines has evolved from pure mechanical control to PLC-dominated systems. Traditional control systems have gradually revealed obvious defects and deficiencies in terms of real-time performance, collaboration, and intelligence, making it difficult to meet the high requirements of modern production. Therefore, it is necessary to combine edge-cloud collaboration technology for intelligent and accurate control.

[0003] Reference patent application CN113534728A discloses a screw processing machine control system, including a screw processing machine that processes screws and detects processing data with at least one sensor, the processing data including at least voltage and current values; a conveying unit, one end of which is connected to the screw processing machine to receive processed screws, the other end of which is divided into a qualified product channel and a defective product channel, and a screening valve is provided between the qualified product channel and the defective product channel; a machine control box, which connects the screw processing machine and the conveying unit, the machine control box having a programmable controller built inside, the programmable controller controlling the conveying unit to convey processed screws, and controlling the timing of the screening valve flipping. Existing edge-cloud collaborative control systems typically employ a holistic approach to collect and analyze the operating status of screw processing machines. This allows for dynamic analysis over a significant time span. However, this holistic approach fails to account for the high workload associated with centralized data parameter analysis. Furthermore, it cannot accurately and independently collect relevant parameters at different specific moments during the screw processing stage. Consequently, data parameters become relatively concentrated and congested during transmission and interaction between the machine and the cloud. This can easily lead to delays and confusion in the transmission of some data parameters, resulting in data parameter discretization and reducing the safety and reliability of edge-cloud collaborative control.

[0004] In view of this, the present invention proposes a control system for screw processing machine based on end-to-end cloud collaboration to solve the above problems. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art and to achieve the above objectives, the present invention provides the following technical solution: a control system for a screw processing machine based on end-to-end cloud collaboration, applied to a collaborative controller, comprising: The parameter acquisition module is used to divide the screw processing stage into continuous sub-stages, including idle stage, thread rolling stage and return stage. Several sub-stages are spliced ​​together to form a control cycle with periodic units with interval distribution, and the real-time processing parameters of the logic processing machine are collected during the control cycle. The model recognition module is used to query the attribute parameters of the screw workpiece, receive the requirement parameters of the screw workpiece, determine the operating parameters of the screw processing machine, summarize the attribute parameters, requirement parameters and operating parameters into a collaborative parameter set, and identify the standard processing parameters corresponding to the collaborative parameter set through a deep learning model. The control analysis module is used to adapt and analyze the real-time processing parameters with the standard processing parameters, draw the stability curve of the screw processing machine in the control cycle, and analyze the reliability of the screw processing machine in the control cycle based on the point normalization criterion to determine whether to execute the collaborative control mode. The collaborative control module is used to identify the parameters to be adjusted from the real-time processing parameters in collaborative control mode, determine the collaborative control sequence of the parameters to be adjusted, and perform collaborative control operations on the screw processing machine through the collaborative controller based on the parameters to be adjusted and the collaborative control sequence.

[0006] Furthermore, the method for splicing the control cycle is as follows: Two idle stages and one thread rolling stage in the same screw processing stage are combined into a cycle unit to obtain A cycle units. Arrange the A cycle units in chronological order, and mark the first idle phase in the first cycle unit as the start phase and the second idle phase in the last cycle unit as the end phase. The first moment of the starting phase and the last moment of the ending phase are retrieved by timestamp, and recorded as the start moment and the end moment, respectively. The time period between the start moment and the end moment is recorded as the control period.

[0007] Furthermore, real-time processing parameters include dynamic contact pressure value, stroke balance value, unit flow rate value, and thread rolling offset value; The method for collecting the wire twist offset value is as follows: The time period during the thread rolling stage is recorded as the thread rolling period, and A thread rolling periods are obtained. A top-down video of the screw workpiece during the A thread rolling periods is captured by a camera. Using a preset interval as a standard, B top-view images are extracted from the top-view video. Edge detection technology is used to identify the edge line of the screw workpiece head, and the area inside the edge line is recorded as the head area. Draw the bisecting lines of the head area along the horizontal and vertical directions respectively, and record the intersection of the two bisecting lines as the center point. Arrange the B top view images one by one according to the twisting direction, and then connect the B center points in sequence to form the twisting center line. The part of the thread rolling centerline that does not coincide with the standard centerline is recorded as the offset line. The length of the offset line in A top view images is compared with the length of the thread rolling centerline to obtain A thread rolling offset values.

[0008] Furthermore, the attribute parameters include material type, screw length, and screw diameter; the requirement parameters include thread rolling depth and thread rolling length; and the operating parameters include thread rolling speed, operating current, operating temperature, and feeding rate.

[0009] Furthermore, standard processing parameters include standard pressure values, standard equilibrium values, standard flow rate values, and standard offset values.

[0010] Furthermore, the stability curves include pressure curves, stroke curves, flow velocity curves, and offset curves; the method for drawing stability curves is as follows: The pressure difference is calculated by subtracting the dynamic contact pressure value from the standard pressure value and taking the absolute value. The difference between the travel balance value and the standard balance value is calculated by taking the absolute value. The velocity difference is calculated by subtracting the unit velocity value from the standard velocity value and taking the absolute value. The offset difference is calculated by subtracting the thread twist offset value from the standard offset value and taking the absolute value. According to the chronological order, the A periodic units are numbered in ascending order, and four coordinate axes are drawn with the number as the horizontal axis and the pressure difference, stroke difference, flow rate difference, and offset difference as the vertical axis. Starting from the pressure threshold, stroke threshold, flow rate threshold, and offset threshold, pressure lines, stroke lines, flow rate lines, and offset lines are drawn on the vertical axis of the four coordinate axes respectively. Mark the points corresponding to the pressure difference, stroke difference, flow rate difference, and offset difference of A cycle units on the four coordinate axes respectively. Then, connect all the points on the same coordinate axis in sequence to draw the pressure curve, stroke curve, flow rate curve, and offset curve.

[0011] Furthermore, the point normalization criterion is: abnormal points under the same number are classified into the same point set; Reliability includes safe reliability and dangerous unreliability; the method of reliability analysis is as follows: Points located above the pressure line, stroke line, velocity line, and offset line are recorded as abnormal points. After summing up the abnormal points under the same number, a set of A points is obtained. Count the number of abnormal points in the A point sets in ascending order of their numbers. Record the set of points with an abnormal number greater than or equal to 1 as the abnormal set and record the number of the abnormal set as the abnormal number. Record at least three consecutive anomaly numbers as an anomaly group, count the number of anomaly groups, record the anomaly value, and record one-third of the number of points in the set as the standard value. When there are 3 or more abnormal values ​​or the number of abnormal sets within the control cycle, the reliability is dangerously unreliable. The reliability is considered safe and reliable when there are no abnormal values ​​greater than or equal to 3 or the number of abnormal sets exceeds the calibrated value within the control period.

[0012] Furthermore, the method for determining whether to execute the collaborative control mode is as follows: When the reliability of the screw processing machine is deemed safe and reliable, the collaborative control mode is not executed. When the reliability of the screw processing machine is deemed dangerously unreliable, the collaborative control mode is executed.

[0013] Furthermore, the method for identifying the parameters to be adjusted is as follows: When the abnormal point is a pressure difference value, the dynamic contact pressure value is recorded as the parameter to be adjusted; When the abnormal point is a travel difference, the travel balance value is recorded as the parameter to be adjusted; When the abnormal point is a flow velocity difference, the unit flow velocity value is recorded as the parameter to be adjusted; When the abnormal point is the offset difference, the wire twisting offset value is recorded as the parameter to be adjusted.

[0014] Furthermore, the method for coordinated control operations is as follows: The parameters to be adjusted, arranged in order, are sent to the collaborative controller in sequence, which then drives the collaborative controller to associate with the corresponding processing mechanism. When the parameter to be adjusted is the dynamic contact pressure value, the associated pressure regulating mechanism and the cooperating controller adjust the lifting amplitude of the hydraulic cylinder in the pressure regulating mechanism until the dynamic contact pressure value is consistent with the standard pressure value; When the parameter to be adjusted is the stroke balance value, the associated stroke adjustment mechanism and the co-controller adjust the lifting amplitude of the hydraulic cylinder in the stroke adjustment mechanism until the stroke balance value is consistent with the standard balance value. When the parameter to be adjusted is the unit flow rate value, the associated cooling oil regulating mechanism and the co-controller adjust the pumping power of the oil pump in the cooling oil regulating mechanism until the unit flow rate value is consistent with the standard flow rate value. When the parameter to be adjusted is the thread rolling offset value, the associated offset adjustment mechanism and the co-controller adjust the lifting amplitude of the hydraulic cylinder in the offset adjustment mechanism until the thread rolling offset value is consistent with the standard offset value.

[0015] The technical advantages of the control system for a screw processing machine based on edge-cloud collaboration of the present invention are as follows: (1): By dividing the screw processing stage into sub-stages and sequentially splicing the idle stage and the thread rolling stage into a control cycle, this invention can accurately mark the local time period that affects the thread rolling quality of the screw workpiece, shorten the time span of relevant parameter collection, and avoid the high burden brought by the overall screw processing stage with a large time span during data collection. At the same time, by splicing the control cycle with periodic units with interval distribution, the evaluation process of the screw processing machine can be divided into interval and cyclical operations, which reserves a reasonable redundant buffer time for data transmission and interaction between the machine end and the cloud, improves the data interactivity between the machine end and the cloud, avoids the phenomenon of data dispersion and chaos, and thus provides a security guarantee for end-to-cloud collaborative control.

[0016] (2): This invention can reliably evaluate the actual operating status of the screw processing machine at different specific times within the control cycle by adapting and analyzing the real-time processing parameters and standard processing parameters and drawing multiple types of stability curves. This achieves the parallel synchronous analysis effect of the screw processing machine in multiple dimensions, avoids the limitations of the overall summary analysis method in the same time period, and provides a precise theoretical basis for end-to-cloud collaborative control operation, thereby meeting the control requirements of end-to-cloud collaboration. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of a control system for a screw processing machine based on end-to-cloud collaboration, provided in Embodiment 1 of the present invention. Figure 2 This is a schematic diagram of the pressure curve provided in Embodiment 1 of the present invention; Figure 3 This is a schematic diagram of the stroke curve provided in Embodiment 1 of the present invention; Figure 4 This is a schematic diagram of the flow velocity curve provided in Embodiment 1 of the present invention; Figure 5 This is a schematic diagram of the offset curve provided in Embodiment 1 of the present invention; Figure 6 This is a flowchart illustrating a control method for a screw processing machine based on end-to-cloud collaboration, as provided in Embodiment 2 of the present invention. Detailed Implementation

[0018] 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 embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] Example 1: Please refer to Figures 1-5 As shown in the figure, the control system for a screw processing machine based on edge-cloud collaboration described in this embodiment is applied to a collaborative controller and includes: The parameter acquisition module divides the screw processing stage into continuous sub-stages, splices multiple spaced sub-stages into a control cycle, and acquires the real-time processing parameters of the logic processing machine during the control cycle. The screw processing stage refers to the entire process involved in the screw thread rolling process, enabling the screw processing stage to represent the complete screw thread rolling process.

[0020] Since the screw processing machine performs the screw rolling process through the reciprocating motion of the moving and stationary thread rolling plates, the screw processing stage also includes different sub-stages to distinguish whether the thread rolling plate comes into contact with the screw. In this embodiment, the sub-stages include an idle stage, a yarn rolling stage, and a return stage.

[0021] The idle stage refers to the stage in which the moving and stationary thread rolling plates of the screw processing machine do not contact the screw workpiece during forward thread rolling. Specifically, a screw processing stage contains two non-continuous idle stages, which correspond to the stages before and after the stationary thread rolling plate contacts the screw workpiece during forward movement.

[0022] The thread rolling stage refers to the stage in which the moving and stationary thread rolling plates of the screw processing machine perform forward thread rolling with the screw workpiece; specifically, the preceding and following sub-stages of the thread rolling stage are both idle stages.

[0023] The return phase refers to the phase when the moving thread rolling plate of the screw processing machine moves in the reverse direction; specifically, the sub-phase before and after the return phase are both idle phases.

[0024] It should be noted that a screw processing stage consists of two idle stages, one thread rolling stage, and one return stage; and according to the order of the thread rolling processing time of the screw workpiece, the sub-stages are arranged in the following order according to the timeline: idle stage, thread rolling stage, idle stage, and return stage.

[0025] The control cycle is the corresponding duration used to analyze and control the operating status of the screw processing machine during screw processing. It ensures that the screw processing machine can be analyzed and controlled regularly within a control cycle, and also ensures that there is sufficient data information within a control cycle. In this embodiment, the control period is a time period obtained by splicing together multiple interval-distributed sub-stages on the timeline.

[0026] Specifically, the method for splicing control cycles is as follows: Two idle stages and one thread rolling stage in the same screw processing stage are combined into a cycle unit to obtain A cycle units. Arrange the A cycle units in chronological order, and mark the first idle phase in the first cycle unit as the start phase and the second idle phase in the last cycle unit as the end phase. The first moment of the starting phase and the last moment of the ending phase are retrieved by timestamp, and recorded as the start moment and the end moment, respectively. The time period between the start moment and the end moment is recorded as the control period.

[0027] It should be noted that the specific duration of the control cycle is not fixed. It is determined by the actual time span between the start and end stages of the screw processing machine, and the time span between the start and end stages is also affected by factors such as the movement length and speed of the moving thread rolling plate.

[0028] Once the control cycle is determined, relevant parameters of the screw processing machine can be collected within the control cycle. These collected parameters can be used to represent the actual operating status of the screw processing machine and serve as the object for subsequent coordinated control of the screw processing machine. These parameters are also recorded as real-time processing parameters. In this embodiment, the real-time processing parameters refer to the actual parameters of the screw processing machine when it performs thread rolling processing on the screw workpiece within the control cycle. Specifically, real-time processing parameters include dynamic contact pressure value, stroke balance value, unit flow rate value, and wire rolling offset value.

[0029] The dynamic contact pressure value refers to the thread rolling pressure of the moving thread rolling plate and the stationary thread rolling plate when rolling the screw workpiece during the control cycle, so that the dynamic contact pressure value can affect the thread rolling depth on the screw workpiece. The dynamic contact pressure value is obtained by detecting the maximum pressure value of the moving thread rolling plate and the stationary thread rolling plate when rolling the screw workpiece in A cycle units by a pressure sensor.

[0030] The stroke balance value refers to the maximum displacement length of the moving thread rolling plate during the thread rolling process of the screw workpiece within the control cycle, which can represent the integrity of the thread rolling of the screw workpiece; the stroke balance value is obtained by detecting the maximum displacement value in each of the A cycle units by the displacement sensor.

[0031] The unit flow rate value refers to the unit flow rate of cooling oil flowing to the moving and stationary thread rolling plates within the control cycle, which can be used to represent the cooling performance of the screw processing machine. The unit flow rate value is obtained by detecting the flow rate value in A cycle units one by one by the flow rate sensor.

[0032] The thread rolling offset value refers to the extent to which the center of the screw workpiece tilts left or right during the thread rolling process within the control cycle, which can be used to represent the screw balance of the screw workpiece. The method for collecting the wire twist offset value is as follows: The time period during the thread rolling stage is recorded as the thread rolling period, and A thread rolling periods are obtained. A top-down video of the screw workpiece during the A thread rolling periods is captured by a camera. Using a preset interval as a standard, B top-view images are extracted from the top-view video. Edge detection technology is used to identify the edge line of the screw workpiece head, and the area inside the edge line is recorded as the head area. The preset interval refers to the time span between two adjacent top-view images, which allows for the extraction of a sufficient number of top-view images from the top-view video. In this embodiment, the preset interval can be set as needed, or it can be set according to the displacement length and displacement speed of the moving thread rolling plate. Specifically, the larger the displacement length, the larger the preset interval; the larger the displacement speed, the smaller the preset interval. Draw the bisecting lines of the head area along the horizontal and vertical directions respectively, and record the intersection of the two bisecting lines as the center point. Arrange the B top view images one by one according to the twisting direction, and then connect the B center points in sequence to form the twisting center line. After superimposing the thread rolling center line with the standard center line, the overlap is compared. The part of the thread rolling center line that does not overlap with the standard center line is recorded as the offset line. The length of the offset line is measured. The length of the offset line of each of the A top view images is compared with the length of the thread rolling center line to obtain A thread rolling offset values.

[0033] It should be noted that the number of dynamic contact pressure values, stroke balance values, unit flow rate values, and wire rolling offset values ​​collected are all A, so that each cycle unit corresponds to one dynamic contact pressure value, stroke balance value, unit flow rate value, and wire rolling offset value.

[0034] The parameter recognition module queries the attribute parameters of the screw workpiece, receives the required parameters for screw processing, determines the operating parameters of the screw processing machine, and summarizes the attribute parameters, required parameters, and operating parameters into a collaborative parameter set. It then identifies the standard processing parameters through a deep learning model. Attribute parameters are used to represent the information parameters of the material and structure of the screw workpiece itself, so that attribute parameters can be used as one of the factors affecting the setting and selection of standard processing parameters of screw processing machine. Specifically, the attribute parameters include material type, screw length, and screw diameter.

[0035] The material type value is a numerical value used to specify the type of metal material used to manufacture the screw. Specifically, the metal material types include, but are not limited to, steel, iron, steel alloys, nickel alloys, etc., and each attribute material type corresponds to a different value. For example, the material type values ​​for steel, iron, and steel alloys are G1, T1, GT, and NJ, respectively.

[0036] The screw length value and screw diameter value refer to the length and diameter of the screw workpiece, respectively, which can be used to represent the dimensions of the screw workpiece during thread rolling.

[0037] The requirement parameters are used to represent information parameters such as the thread rolling size and structure of the screw workpiece when performing thread rolling processing, which can be used as the thread rolling processing requirements of the screw workpiece. In this embodiment, the required parameters include the thread rolling depth value and the thread rolling length value; the thread rolling depth value and the thread rolling length value are obtained by manual input or by selection of options.

[0038] Specifically, the thread rolling depth value refers to the depth of each thread recess when the screw workpiece is thread rolled; the thread rolling length value refers to the length of all threads in the body of the screw workpiece when the screw workpiece is thread rolled.

[0039] Operating parameters are the information of various parameters set by the screw processing machine when it is performing thread rolling on screw workpieces, and can be used as the basis for the normal operation of the screw processing machine. Specifically, the operating parameters include wire rolling speed, operating current, operating temperature, and feeding rate; Thread rolling speed refers to the unit movement speed of the moving thread rolling plate when it is rolling threads on a screw workpiece. It can be used to express how fast the moving thread rolling plate moves. Specifically, the thread rolling speed is affected by the spindle speed on the screw processing machine. The higher the spindle speed, the higher the thread rolling speed will be.

[0040] The operating current refers to the rated current of the screw processing machine when performing thread rolling; the operating temperature refers to the rated temperature of the screw processing machine when performing thread rolling.

[0041] The feeding rate refers to the number of screw workpieces supplied by the feeding mechanism to the thread rolling mechanism per unit time when the screw processing machine is performing thread rolling. The higher the feeding rate, the more screw workpieces are supplied per unit time.

[0042] Standard processing parameters refer to the standard parameters used by the screw processing machine to roll screws within the control cycle. In this embodiment, the types of parameters corresponding to the standard processing parameters and the real-time processing parameters are consistent, and the specific content referred to by the standard processing parameters and the real-time processing parameters is also consistent. Specifically, since real-time processing parameters include dynamic contact pressure value, stroke balance value, unit flow rate value, and thread rolling offset value, standard processing parameters include standard pressure value, standard balance value, standard flow rate value, and standard offset value.

[0043] In this embodiment, the standard processing parameters are not obtained randomly, but are identified by deep learning through a deep learning model based on attribute parameters, demand parameters, and operating parameters. Deep learning models are obtained by using deep learning technology, combining a large set of collaborative parameters and corresponding standard processing parameters, and continuously optimizing and iterating them during training.

[0044] When identifying standard processing parameters using a deep learning model, attribute parameters, requirement parameters, and operational parameters need to be aggregated into a collaborative parameter set, so that the collaborative parameter set serves as the input data for the deep learning model, and the standard processing parameters serve as the output data for the deep learning model.

[0045] Specifically, the method for identifying standard processing parameters is as follows: Multiple sets of attribute parameters, demand parameters, operating parameters and standard processing parameters of screw processing machine are collected in advance within a historical period. After summarizing the attribute parameters, demand parameters and operating parameters of the same set, a set of collaborative parameters is generated, resulting in multiple sets of collaborative parameters and multiple sets of standard processing parameters. Each set of collaborative parameters is labeled as a training feature, and the standard processing parameters corresponding to each set of training features are labeled. The labeled training features are divided into a training set and a test set; 80% of the training features are used as the training set and 20% of the training features are used as the test set; the deep learning model is trained using the training set and tested using the test set. A preset error threshold is set. When the mean of the prediction error of all training features in the test set is less than the preset error threshold, a deep learning model that identifies standard processing parameters based on the collaborative parameter set is obtained.

[0046] After obtaining the deep learning model, the collected attribute parameters, requirement parameters, and operating parameters can be summarized into a collaborative parameter set. This collaborative parameter set is then input into the deep learning model for deep learning, and the corresponding standard processing parameters are output.

[0047] The control analysis module adapts and analyzes the real-time processing parameters with the standard processing parameters, plots the stability curve of the screw processing machine in the control cycle, and performs a reliability analysis on the screw processing machine based on the point-position normalization criterion to determine whether to execute the collaborative control mode. After obtaining the real-time processing parameters and the standard processing parameters, the real-time processing parameters and the standard processing parameters can be adapted and analyzed to compare the actual state of the screw processing machine in the control cycle. Based on the comparison results, a stability curve can be drawn that reflects the strength of the actual operation stability of the screw processing machine in the control cycle. In this embodiment, the stability curve is a graph used to represent the actual thread rolling operation status changes of the screw processing machine within the control cycle; specifically, the stability curve includes a pressure curve, a stroke curve, a flow rate curve, and an offset curve.

[0048] Specifically, the method for plotting the stability curve is as follows: The pressure difference is calculated by subtracting the dynamic contact pressure value from the standard pressure value and taking the absolute value. The formula for calculating the pressure difference is: ; In the formula, This is the pressure difference. This is the dynamic contact pressure value. This is the standard pressure value; The difference between the travel balance value and the standard balance value is calculated by taking the absolute value. The formula for calculating the travel difference is: ; In the formula, This is the travel difference. This is the travel balance value. This is the standard equilibrium value; The velocity difference is calculated by subtracting the unit velocity value from the standard velocity value and taking the absolute value. The formula for calculating the velocity difference is: ; In the formula, This is the difference in flow velocity. The value is the unit flow velocity. Standard flow rate value; The offset difference is calculated by subtracting the thread twist offset value from the standard offset value and taking the absolute value. The formula for calculating the offset difference is: ; In the formula, This is the offset difference. This is the thread twisting offset value. This is the standard offset value; Following the chronological order, the A cycle units within the control cycle are sequentially numbered in ascending order, and four coordinate axes are plotted with the number as the horizontal axis and the pressure difference, stroke difference, flow rate difference, and offset difference as the vertical axis. The pressure threshold, stroke threshold, flow rate threshold, and offset threshold are marked on the vertical axis of the four coordinate axes respectively. Starting from the pressure threshold, stroke threshold, flow rate threshold, and offset threshold, horizontally distributed pressure lines, stroke lines, flow rate lines, and offset lines are drawn. The pressure threshold, stroke threshold, flow rate threshold, and offset threshold refer to the maximum values ​​of the pressure difference, stroke difference, flow rate difference, and offset difference of the screw processing machine under normal conditions, respectively. These values ​​can be used as data to determine whether the screw processing machine has any abnormal phenomena in the current control cycle. Mark the points corresponding to the pressure difference, stroke difference, flow rate difference, and offset difference of A cycle units on the four coordinate axes respectively. Then, connect all the points on the same coordinate axis in sequence to draw the pressure curve, stroke curve, flow rate curve, and offset curve.

[0049] Based on the above method for drawing stability curves, the required pressure curve, stroke curve, flow velocity curve, and offset curve are drawn respectively, wherein the number of periodic units is 13; for example, Figure 2 This is a pressure curve; the pressure threshold is 1.7 MPa. Figure 3 This is a travel curve graph with a travel threshold of 1.3cm. Figure 4 The graph shows the flow rate, with a flow rate threshold of 0.7 L / min. Figure 5 This is an offset curve, with an offset threshold of 1.8%.

[0050] After obtaining the stability curve of the screw processing machine within the control cycle, the actual operating status and performance of the screw processing machine can be analyzed. Therefore, it is necessary to conduct a reliability analysis on the stability curve within the control cycle to determine whether any abnormal phenomena have occurred in the screw processing machine within the control cycle. The purpose of reliability analysis on the stability curve is to determine the severity of abnormal phenomena in each cycle unit of the screw processing machine and to provide a basis for judgment on whether to carry out subsequent collaborative optimization and control operations.

[0051] When analyzing stability curves, since the number of stability curves is not unique, it is necessary to ensure that the points in multiple stability curves remain consistent on the timeline under the constraint of the point normalization criterion, so as to represent the operating status of the screw processing machine in the same time period. Specifically, the point unification criterion is to classify abnormal points under the same number into the same point set; this can achieve the effect of breaking down the control cycle into smaller, multi-period analysis, and improve the accuracy of analysis and evaluation of screw processing machines within the control cycle.

[0052] Reliability is used to express whether the actual thread rolling process of a screw processing machine is safe and reliable within the control cycle. Specifically, reliability includes safe and reliable and dangerous and unreliable. The method for reliability analysis is as follows: In the pressure curve, stroke curve, flow velocity curve and offset curve, the points located above the pressure line, stroke line, flow velocity line and offset line are recorded as abnormal points. After summing the abnormal points under the same number, a set of A points is obtained. Count the number of abnormal points in the A point sets in ascending order of their numbers. Record the set of points with an abnormal number greater than or equal to 1 as the abnormal set and record the number of the abnormal set as the abnormal number. Record at least three consecutive anomaly numbers as an anomaly group, count the number of anomaly groups, record the anomaly value, and record one-third of the number of points in the set as the standard value. When there are 3 or more abnormal values ​​or the number of abnormal sets within the control cycle, the screw processing machine has experienced a serious abnormality within the control cycle. At this time, the reliability and stability of the screw processing machine during the control cycle are poor, and the reliability of the screw processing machine is dangerous and unreliable. When there are no abnormal values ​​greater than or equal to 3 or the number of abnormal sets exceeds the calibrated value within the control cycle, the screw processing machine does not exhibit any serious abnormal phenomena within the control cycle. In this case, the screw processing machine operates with good reliability and stability within the control cycle, and the screw processing machine is considered safe and reliable.

[0053] The collaborative control mode is a working mode used to perform end-to-cloud collaborative control when abnormal phenomena occur in the control cycle of the screw processing machine, and serves as the basis for subsequent control of the screw processing mechanism. Specifically, the method for determining whether to execute the collaborative control mode is as follows: When the reliability of the screw processing machine is safe and reliable within the control cycle, the screw processing machine does not need to perform end-to-cloud collaborative control processing, and it is determined that the collaborative control mode will not be executed. When the reliability of the screw processing machine is dangerously unreliable during the control cycle, the screw processing machine needs to undergo end-to-end cloud collaborative control processing, and the collaborative control mode is then executed.

[0054] The collaborative control module, in collaborative control mode, identifies the parameters to be adjusted from the real-time processing parameters, determines the collaborative control sequence of the parameters to be adjusted, and performs collaborative control operations on the screw processing machine through the collaborative controller. In the collaborative control mode, the screw processing machine needs to be controlled accordingly so that it can maintain a normal and efficient operating state in the next control cycle, thereby improving the screw processing machine's thread rolling quality and efficiency. The parameters to be adjusted refer to the real-time processing parameters that need to be adjusted and optimized in the next control cycle, so as to achieve the end-to-cloud collaborative control effect of the screw processing machine from the mechanical end to the cloud and back to the mechanical end.

[0055] Specifically, the method for identifying the parameters to be adjusted is as follows: When the abnormal point is the pressure difference value, the screw rolling pressure of the screw processing machine has an abnormal phenomenon within the control cycle. Then the moving contact pressure value is recorded as the parameter to be adjusted. When the abnormal point is the stroke difference, the screw processing machine has an abnormal thread rolling stroke within the control cycle. The stroke balance value is then recorded as the parameter to be adjusted. When the abnormal point is the flow rate difference, it means that the cooling oil flow rate of the screw processing machine is abnormal within the control cycle. The unit flow rate value is then recorded as the parameter to be adjusted. When the abnormal point is the offset difference, it means that the screw processing machine has an abnormal tilt in the thread rolling process within the control cycle. The thread rolling offset value is then recorded as the parameter to be adjusted.

[0056] The collaborative control sequence is the order in which the corresponding mechanisms of the screw processing machine are coordinated and controlled. It serves as the basis for end-to-end collaborative control of the parameters to be adjusted, thereby avoiding the phenomenon of crossover and confusion when multiple parameters to be adjusted are coordinated and improving the orderly coordination of the parameters to be adjusted on the screw processing machine. In this embodiment, when determining the order of coordinated control, it is necessary to base it on the number of parameters to be adjusted within the control cycle. Specifically, the number of abnormal points where the parameters to be adjusted are pressure difference, stroke difference, flow rate difference and offset difference are counted respectively to obtain the value to be adjusted, and all the parameters to be adjusted are arranged in order from large to small according to the value to be adjusted.

[0057] Once the control sequence is determined, the relevant mechanisms of the screw processing machine can be controlled remotely via the collaborative controller to eliminate the negative impact of the parameters to be adjusted in the next control cycle, thereby achieving the effect of collaborative control. Specifically, the method for coordinated control operations is as follows: The parameters to be adjusted, arranged in sequence, are sent to the collaborative controller in turn, which then drives the collaborative controller to associate with the corresponding processing mechanism. The processing mechanism is used to perform complete thread rolling processing on the auxiliary screw workpiece in the screw processing machine. Specifically, the processing mechanism includes a pressure adjustment mechanism, a stroke adjustment mechanism, a cooling oil adjustment mechanism, and an offset adjustment mechanism. When the parameter to be adjusted is the moving contact pressure value, the associated processing mechanism is the pressure regulating mechanism. At this time, the co-controller sends co-control information to the pressure regulating mechanism to adjust the lifting amplitude of the hydraulic cylinder in the pressure regulating mechanism, increase or decrease the pressure of the moving thread rolling plate on the screw workpiece, and drive the moving contact pressure value to be consistent with the standard pressure value. When the parameter to be adjusted is the stroke balance value, the associated machining mechanism is the stroke adjustment mechanism. At this time, the co-controller sends co-control information to the stroke adjustment mechanism to adjust the lifting amplitude of the hydraulic cylinder in the stroke adjustment mechanism, increase or decrease the thread rolling displacement amplitude of the moving thread rolling plate, and drive the stroke balance value to be consistent with the standard balance value. When the parameter to be adjusted is the unit flow rate value, the associated processing mechanism is the cooling oil regulating mechanism. At this time, the co-controller sends co-control information to the cooling oil regulating mechanism to adjust the pumping power of the oil pump in the cooling oil regulating mechanism, increase or decrease the unit flow rate of the cooling oil, and drive the unit flow rate value to be consistent with the standard flow rate value. When the parameter to be adjusted is the thread rolling offset value, the associated processing mechanism is the offset adjustment mechanism. At this time, the co-controller sends co-control information to the offset adjustment mechanism to adjust the lifting amplitude of the hydraulic cylinder in the offset adjustment mechanism, reduce the tilt amplitude between the moving thread rolling plate and the stationary thread rolling plate, and drive the thread rolling offset value to be consistent with the standard offset value.

[0058] Example 2: Please refer to Figure 6 As shown, parts not described in detail in this embodiment are described in Embodiment 1. This embodiment provides a control method for a screw processing machine based on edge-cloud collaboration, applied to a collaborative controller. It is implemented based on a control system for a screw processing machine based on edge-cloud collaboration, including: S01: Divide the screw processing stage into continuous sub-stages, including idle stage, thread rolling stage and return stage. Splice several sub-stages into a control cycle with periodic units with interval distribution, and collect the real-time processing parameters of the logic processing machine in the control cycle. S02: Query the attribute parameters of the screw workpiece, receive the demand parameters of the screw workpiece, determine the operating parameters of the screw processing machine, summarize the attribute parameters, demand parameters and operating parameters into a collaborative parameter set, and identify the standard processing parameters corresponding to the collaborative parameter set through a deep learning model. S03: Perform adaptation analysis between real-time processing parameters and standard processing parameters, plot the stability curve of the screw processing machine in the control cycle, and analyze the reliability of the screw processing machine in the control cycle based on the point-to-position normalization criterion to determine whether to execute the collaborative control mode; if the collaborative control mode is executed, proceed to S04; if the collaborative control mode is not executed, end. S04: In the collaborative control mode, the parameters to be adjusted are identified from the real-time processing parameters, the collaborative control sequence of the parameters to be adjusted is determined, and the collaborative controller is used to perform collaborative control operations on the screw processing machine based on the parameters to be adjusted and the collaborative control sequence.

[0059] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A control system of a screw processing machine based on end-cloud cooperation, applied to a cooperative controller, characterized in that, The method comprises the following steps: A parameter acquisition module is used to divide a screw machining stage into continuous sub-stages, including an idle stage, a wire rolling stage and a return stage, splice a plurality of sub-stages into a control period with interval distribution of periodic units, and collect real-time machining parameters of a logical machining platform in the control period; A model identification module is used to query attribute parameters of a screw workpiece, receive demand parameters of the screw workpiece, determine operation parameters of a screw machining platform, and integrate the attribute parameters, the demand parameters and the operation parameters into a collaborative parameter set, and identify standard machining parameters corresponding to the collaborative parameter set through a deep learning model; A control analysis module is used to perform adaptive analysis on the real-time machining parameters and the standard machining parameters, draw a stability curve of the screw machining platform in the control period, analyze the reliability of the screw machining platform in the control period based on a point position normalization criterion, and determine whether to execute a collaborative control mode; A collaborative control module is used to identify to-be-adjusted parameters from the real-time machining parameters in the collaborative control mode, determine a collaborative control sequence of the to-be-adjusted parameters, and perform collaborative control operations on the screw machining platform through a collaborative controller based on the to-be-adjusted parameters and the collaborative control sequence.

2. The control system of a screw processing machine table based on end-cloud cooperation according to claim 1, characterized in that, The splicing method of the control period comprises the following steps: Two idle stages and one wire rolling stage in the same screw machining stage are combined into one periodic unit, and A periodic units are obtained; The A periodic units are arranged in sequence according to the time sequence, the first idle stage in the first periodic unit is recorded as a starting stage, and the second idle stage in the last periodic unit is recorded as a termination stage; The first time point of the starting stage and the last time point of the termination stage are queried through timestamps, which are recorded as a starting time point and a termination time point, and a time period between the starting time point and the termination time point is recorded as a control period.

3. The control system of a screw processing machine table based on end-cloud cooperation according to claim 2, characterized in that, The real-time machining parameters include a dynamic contact pressure value, a stroke balance value, a unit flow rate value and a wire rolling offset value; The acquisition method of the wire rolling offset value comprises the following steps: A time period in the wire rolling stage is recorded as a wire rolling time period, A wire rolling time periods are obtained, and a camera is used to shoot overhead videos of the screw workpiece in the A wire rolling time periods; B overhead images are cut from the overhead videos according to a preset interval length, an edge detection technology is used to identify an edge line of a head of the screw workpiece, and a region inside the edge line is recorded as a head region; A bisector of the head region is drawn along a horizontal direction and a vertical direction respectively, an intersection of the two bisectors is recorded as a center point, B overhead images are arranged in sequence according to a wire rolling direction, and the B center points are sequentially connected to form a wire rolling center line; A part of the wire rolling center line that does not coincide with a standard center line is recorded as an offset line, and a length of the offset line in the A overhead images is compared with a length of the wire rolling center line to obtain A wire rolling offset values.

4. The control system of a screw processing machine table based on end-cloud cooperation according to claim 3, characterized in that, The attribute parameters include a material type value, a screw length value and a screw diameter value; the demand parameters include a wire rolling depth value and a wire rolling length value; and the operation parameters include a wire rolling speed, a working current, a working temperature and a feeding rate.

5. The control system of a screw processing machine table based on end-cloud cooperation according to claim 4, characterized in that, The standard machining parameters include a standard pressure value, a standard balance value, a standard flow rate value and a standard offset value.

6. The control system of a screw processing machine table based on end-cloud cooperation according to claim 5, characterized in that, The stable curve diagram includes a pressure curve diagram, a stroke curve diagram, a flow rate curve diagram, and a deviation curve diagram; the drawing method of the stable curve diagram is: The pressure difference value is calculated by taking the absolute value of the difference between the dynamic contact pressure value and the standard pressure value; The stroke difference value is calculated by taking the absolute value of the difference between the stroke equalization value and the standard equalization value; The flow rate difference value is calculated by taking the absolute value of the difference between the unit flow rate value and the standard flow rate value; The deviation difference value is calculated by taking the absolute value of the difference between the thread rolling deviation value and the standard deviation value; According to the chronological order, the A periodic unit is numbered in ascending order, and the four coordinate axes are drawn with the number as the horizontal axis and the pressure difference value, the stroke difference value, the flow rate difference value, and the deviation difference value as the vertical axis. The pressure threshold value, the stroke threshold value, the flow rate threshold value, and the deviation threshold value are taken as the starting point, and the pressure line, the stroke line, the flow rate line, and the deviation line are drawn on the vertical axis of the four coordinate axes, respectively. The corresponding point positions of the pressure difference value, the stroke difference value, the flow rate difference value, and the deviation difference value of the A periodic unit are marked on the four coordinate axes, respectively, and the pressure curve diagram, the stroke curve diagram, the flow rate curve diagram, and the deviation curve diagram are drawn by sequentially connecting all the point positions on the same coordinate axis.

7. The control system of a screw machine based on end-cloud cooperation according to claim 6, characterized in that, The point position normalization criterion is that the abnormal point positions under the same number are classified into the same point position set; The reliability includes safe reliability and dangerous unreliability; the reliability analysis method is: The point positions above the pressure line, the stroke line, the flow rate line, and the deviation line are recorded as abnormal point positions, and the abnormal point positions under the same number are summarized to obtain A point position sets; According to the number from small to large, the number of abnormal point positions in the A point position sets is counted, the point position set with the number of abnormal point positions greater than or equal to 1 is recorded as an abnormal set, and the number of the abnormal set is recorded as an abnormal number; At least three consecutive abnormal numbers are recorded as an abnormal group, the number of abnormal groups is counted and recorded as an abnormal value, and one third of the number of point position sets is recorded as a calibration value; When there are abnormal values greater than or equal to 3 or the number of abnormal sets exceeds the calibration value in the control period, the reliability is dangerous and unreliable; When there are no abnormal values greater than or equal to 3 or the number of abnormal sets exceeds the calibration value in the control period, the reliability is safe and reliable.

8. The control system of a screw processing machine table based on end-cloud cooperation according to claim 7, characterized in that, The judgment method of whether to execute the cooperative control mode is: When the reliability of the screw processing machine is safe and reliable, it is determined not to execute the cooperative control mode; When the reliability of the screw processing machine is dangerous and unreliable, it is determined to execute the cooperative control mode.

9. The control system of a screw processing machine table based on end-cloud cooperation according to claim 8, wherein, The identification method of the to-be-adjusted parameter is: When the abnormal point position is the pressure difference value, the dynamic contact pressure value is recorded as the to-be-adjusted parameter; When the abnormal point position is the stroke difference value, the stroke equalization value is recorded as the to-be-adjusted parameter; When the abnormal point position is the flow rate difference value, the unit flow rate value is recorded as the to-be-adjusted parameter; When the abnormal point position is the deviation difference value, the thread rolling deviation value is recorded as the to-be-adjusted parameter.

10. The control system of a screw processing machine table based on end-cloud cooperation according to claim 9, wherein, The method of cooperative control operation is: The to-be-adjusted parameters arranged in sequence are sent to the cooperative controller in turn, and the corresponding processing mechanism is driven by the cooperative controller; When the to-be-adjusted parameter is the dynamic contact pressure value, the pressure adjusting mechanism is associated, the cooperative controller adjusts the jacking amplitude of the hydraulic cylinder in the pressure adjusting mechanism until the dynamic contact pressure value and the standard pressure value remain consistent; When the parameter to be adjusted is the stroke balance value, the associated stroke adjusting mechanism cooperates with the controller to adjust the lifting amplitude of the hydraulic cylinder in the stroke adjusting mechanism until the stroke balance value is consistent with the standard balance value; When the parameter to be adjusted is the unit flow rate value, the associated cooling oil adjusting mechanism cooperates with the controller to adjust the pumping power of the oil pump in the cooling oil adjusting mechanism until the unit flow rate value is consistent with the standard flow rate value; When the parameter to be adjusted is the thread rolling deviation value, the associated deviation adjusting mechanism cooperates with the controller to adjust the lifting amplitude of the hydraulic cylinder in the deviation adjusting mechanism until the thread rolling deviation value is consistent with the standard deviation value.

Images