Intelligent control method and system for industrial production under complex working conditions

Abstract

This application relates to the field of industrial production technology, and discloses an intelligent control method and system for industrial production under complex working conditions, applicable to vehicle production. The method includes: collecting environmental parameters of the vehicle production environment through sensors deployed at multiple detection points in the vehicle production environment; aligning the environmental parameters of the vehicle production environment at the sensors at the multiple detection points according to a preset method; determining whether an abnormal working condition exists based on the environmental parameters; adjusting the environmental parameters of the vehicle production environment to eliminate the abnormal working condition when one exists; and predicting the maintenance cycle of the vehicle production environment based on the environmental parameters. This invention optimizes work production management by constructing a closed-loop architecture of "perception-decision-execution," which is beneficial for ensuring production continuity and provides an innovative solution for complex industrial process control in intelligent manufacturing scenarios.

Description

Technical Field

[0001] This invention relates to the field of industrial production technology, and more specifically, to intelligent control methods and systems for industrial production under complex operating conditions. Background Technology

[0002] In the modern vehicle manufacturing sector, intelligent transformation of industrial production has become a core path to improve efficiency and ensure quality. With the increasing complexity of vehicle products (such as new energy vehicles and intelligent driving system integration), the number of multi-source heterogeneous interference factors in the production environment has significantly increased, such as temperature and humidity fluctuations, equipment vibration, and electromagnetic interference. These factors can lead to problems such as assembly accuracy deviations, unstable welding quality, or painting defects. Traditional control methods rely on manual experience to set fixed thresholds, which are difficult to adapt to dynamically changing complex operating conditions and suffer from bottlenecks such as data silos and response delays.

[0003] Therefore, there is an urgent need for an intelligent control method and system for industrial production under complex working conditions, which can automatically sense changes in working conditions and automatically adjust production environment parameters to ensure stable vehicle manufacturing. Summary of the Invention

[0004] In order to solve the above-mentioned technical problems, this application is made to provide an intelligent control method and system for industrial production under complex working conditions, which can automatically sense changes in working conditions and automatically adjust production environment parameters to ensure stable vehicle manufacturing.

[0005] In a first aspect, the present invention provides an intelligent control method for industrial production under complex working conditions, for vehicle production, comprising: collecting environmental parameters of the vehicle production environment through sensors deployed at multiple detection points in the vehicle production environment; aligning the environmental parameters of the vehicle production environment at the sensors at the multiple detection points according to a preset method; determining whether an abnormal working condition exists based on the environmental parameters of the vehicle production environment; adjusting the environmental parameters of the vehicle production environment to eliminate the abnormal working condition when the abnormal working condition exists; and predicting the maintenance cycle of the vehicle production environment based on the environmental parameters of the vehicle production environment when no abnormal working condition exists.

[0006] Optionally, in the aforementioned intelligent control method for industrial production under complex working conditions, aligning the environmental parameters of the vehicle production environment from the sensors at the multiple detection points according to a preset method includes: acquiring the clock time of the sensors at the multiple detection points; calculating the standard deviation of the clock time of the sensors at the multiple detection points; determining whether the standard deviation of the clock time of the sensors at the multiple detection points is higher than a preset first threshold; removing the environmental parameters of the vehicle production environment acquired by sensors whose standard deviation of clock time is higher than the first threshold from the environmental parameters of the vehicle production environment from the sensors at the multiple detection points; determining whether the standard deviation of the clock time of the sensors at the multiple detection points is lower than the first threshold and higher than a preset second threshold; adjusting the clock time of the sensors whose standard deviation of clock time is lower than the first threshold and higher than the second threshold, and adjusting the clock time of the sensor at the i-th detection point among the multiple detection points. , This refers to the clock time of the sensor at the preset master node among the multiple detection points. The clock time of the sensor at the i-th detection point before adjustment is given, where n is the number of detection points. Let be the standard deviation of the clock time of the sensor at the i-th detection point.

[0007] Optionally, in the aforementioned intelligent control method for industrial production under complex working conditions, the environmental parameters of the vehicle production environment include the welding current timing signal of the welding electrode; determining whether an abnormal working condition exists based on the environmental parameters of the vehicle production environment includes: calculating the fluctuation amplitude of the welding current timing signal; determining whether the fluctuation amplitude of the welding current timing signal exceeds a preset amplitude; when the fluctuation amplitude of the welding current timing signal exceeds the preset amplitude, acquiring an image of welding spatter at a preset position; calculating the spatter intensity based on the welding spatter image; determining whether the spatter intensity is higher than a preset intensity; determining that the abnormal working condition exists when the spatter intensity is higher than the preset intensity; adjusting the environmental parameters of the vehicle production environment to eliminate the abnormal working condition includes: adjusting the pressure of the welding electrode to reduce the spatter intensity.

[0008] Optionally, in the aforementioned intelligent control method for industrial production under complex working conditions, calculating the fluctuation amplitude of the welding current timing signal includes: calculating the angular frequency of the welding current timing signal based on the frequency of the current welding power source; calculating the phase angle of the welding current timing signal based on the zero-crossing point of the waveform of the welding current timing signal; and calculating the fluctuation amplitude of the welding current timing signal based on the angular frequency and phase angle of the welding current timing signal.

[0009] Optionally, in the aforementioned intelligent control method for industrial production under complex working conditions, calculating the spatter intensity based on the welding spatter images includes: acquiring multiple consecutive welding spatter images; calculating the spatial gradient and color gradient between each pair of adjacent welding spatter images; detecting the distance between the preset position and the weld; and calculating the spatter intensity based on the spatial gradient and color gradient between each pair of adjacent welding spatter images and the distance between the preset position and the weld.

[0010] Optionally, in the aforementioned intelligent control method for industrial production under complex working conditions, adjusting the pressure of the welding electrode to reduce the spatter intensity includes: setting a spatter sensitivity factor based on the welding material; and calculating a spatter suppression pressure based on the spatter sensitivity factor and the spatter intensity. , For the splash-sensitive factor, The spatter intensity is defined; a heat compensation factor is set based on the coefficient of thermal expansion and elastic modulus of the welding material and the volume of the welding electrode; and a heat compensation pressure is calculated based on the heat compensation factor and the welding temperature. , The coefficient of thermal expansion of the welding material is given. The elastic modulus of the welding material is given. The volume of the welding electrode. Equivalent to the aforementioned thermal compensation factor, Indicates multiplication. Let e ​​be the welding temperature, and e be the base of the natural logarithm function. The softening coefficient of the welding material is given. The room temperature of the vehicle production environment; adjusting the pressure of the welding electrodes. , This is the base pressure of the welding electrode.

[0011] Optionally, in the aforementioned intelligent control method for industrial production under complex working conditions, the environmental parameters of the vehicle production environment include the assembly force feedback data of the assembly robot arm; determining whether an abnormal working condition exists based on the environmental parameters of the vehicle production environment includes: determining whether the assembly force feedback data of the assembly robot arm is higher than a preset threshold; when the assembly force feedback data of the assembly robot arm is higher than the preset threshold, determining that the abnormal working condition exists; adjusting the environmental parameters of the vehicle production environment to eliminate the abnormal working condition includes: adjusting the stiffness matrix of the assembly robot arm to reduce the assembly force feedback data of the assembly robot arm.

[0012] Optionally, in the aforementioned intelligent control method for industrial production under complex working conditions, adjusting the stiffness matrix of the assembly robot arm includes: determining the basic stiffness matrix and stiffness increment based on the assembly material; setting a compensation factor based on the welding temperature; and adjusting the stiffness matrix of the assembly robot arm. , The basic stiffness matrix is... As a preset adjustment factor, The preset reference temperature difference Given the thermal relaxation coefficient of the welding material, The welding temperature is... The preset base temperature, For the stiffness increment, The function is the hyperbolic tangent function. The function is a hyperbolic cosine function. This represents the maximum force exerted on the assembly robot arm. This refers to the assembly force feedback data of the assembly robot arm. Indicates multiplication.

[0013] Secondly, the present invention provides an intelligent control system for industrial production under complex working conditions, used in vehicle production, comprising: a parameter acquisition module, which acquires environmental parameters of the vehicle production environment through sensors deployed at multiple detection points in the vehicle production environment; a parameter alignment module, which aligns the environmental parameters of the vehicle production environment at the multiple detection points according to a preset method; a working condition analysis module, which determines whether there is an abnormal working condition based on the environmental parameters of the vehicle production environment; and a parameter adjustment module, which adjusts the environmental parameters of the vehicle production environment to eliminate the abnormal working condition when the abnormal working condition exists, and predicts the maintenance cycle of the vehicle production environment based on the environmental parameters of the vehicle production environment when the abnormal working condition does not exist.

[0014] The above-described technical solutions of the present invention have at least one or more of the following beneficial effects:

[0015] According to the technical solution of the present invention, by constructing a closed-loop architecture of "perception-decision-execution", the optimization of work production management is realized, which is conducive to ensuring production continuity and provides an innovative solution for complex industrial process control in intelligent manufacturing scenarios, with significant economic benefits and industrial promotion value. Attached Figure Description

[0016] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of this application in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 A flowchart of an intelligent control method for industrial production under complex working conditions according to an embodiment of this application;

[0018] Figure 2 This is a partial flowchart of an intelligent control method for industrial production under complex working conditions according to an embodiment of this application;

[0019] Figure 3 This is another layout flowchart of an intelligent control method for industrial production under complex working conditions according to an embodiment of this application;

[0020] Figure 4 This is another partial flowchart of an intelligent control method for industrial production under complex working conditions according to an embodiment of this application;

[0021] Figure 5 This is a block diagram of an intelligent control system for industrial production under complex operating conditions according to an embodiment of this application. Detailed Implementation

[0022] Some embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0023] like Figure 1 As shown, one embodiment of the present invention provides an intelligent control method for industrial production under complex working conditions, used in vehicle production, comprising:

[0024] Step S110: Collect environmental parameters of the vehicle production environment by using sensors deployed at multiple detection points in the vehicle production environment.

[0025] In this embodiment, changes in environmental factors affect vehicle production, creating complex working conditions such as temperature and humidity fluctuations, equipment vibration, and electromagnetic interference. These factors often lead to welding spatter, abnormal pressure on robotic arms, and other problems, resulting in assembly accuracy deviations, unstable welding quality, or painting defects, thus affecting vehicle production quality.

[0026] Step S120: Align the environmental parameters of the vehicle production environment of the sensors at multiple detection points according to a preset method.

[0027] In this embodiment, a preset spatiotemporal alignment algorithm is used to solve the problem of spatiotemporal misalignment of data from different detection points in traditional sensor networks due to sampling frequency and transmission delay, thereby achieving high-precision spatiotemporal registration of environmental parameters.

[0028] Step S130: Determine whether there is an abnormal operating condition based on the environmental parameters of the vehicle production environment.

[0029] In this embodiment, hidden anomalies under complex working conditions can be identified based on multi-parameter correlation analysis.

[0030] Step S140: When an abnormal operating condition exists, adjust the environmental parameters of the vehicle production environment to eliminate the abnormal operating condition.

[0031] Step S150: When there are no abnormal operating conditions, predict the maintenance cycle of the vehicle production environment based on the environmental parameters of the vehicle production environment.

[0032] In this embodiment, the environmental stability index of the vehicle production environment can be calculated based on parameters such as temperature fluctuation rate, vibration acceleration change, and humidity deviation. When the environmental stability index is too low, the operation and maintenance cycle calculation is triggered. ,in, As the baseline maintenance cycle, , For the preset weights, The aforementioned environmental stability index can be obtained by assigning different weights to each parameter, such as temperature fluctuation rate, vibration acceleration change, and humidity deviation, based on historical experience, and then summing them together. The number of types of parameters such as temperature fluctuation rate, vibration acceleration change, and humidity deviation. For the j-th type parameter The deviation from normal values. Normal values ​​and baseline maintenance cycles are environmental parameters or maintenance cycles corresponding to normal vehicle production or production environment parameters or maintenance cycles obtained from historical experience. This embodiment can reasonably assess the operation and maintenance cycle of the vehicle production environment and prompt timely maintenance of the production environment.

[0033] According to the technical solution of this embodiment, by constructing a closed-loop architecture of "perception-decision-execution", the optimization of work production management is realized, which is conducive to ensuring production continuity and provides an innovative solution for complex industrial process control in intelligent manufacturing scenarios, with significant economic benefits and industrial promotion value.

[0034] like Figure 2 As shown, another embodiment of the present invention provides an intelligent control method for industrial production under complex working conditions. Compared with the aforementioned embodiments, the intelligent control method for industrial production under complex working conditions in this embodiment includes step S120 as follows:

[0035] Step S210: Collect the clock time of the sensors at multiple detection points.

[0036] Step S220: Calculate the standard deviation of the clock time of the sensors at multiple detection points.

[0037] Step S230: Determine whether the standard deviation of the clock time of the sensors at multiple detection points is higher than a preset first threshold.

[0038] Step S240: From the environmental parameters of the vehicle production environment collected by sensors at multiple detection points, remove the environmental parameters of the vehicle production environment collected by sensors whose clock time standard deviation is higher than the first threshold.

[0039] In this embodiment, the accurate identification and isolation of abnormal clock sources are achieved by calculating the standard deviation of multi-sensor clocks in real time. For example, when a sensor's clock drifts due to hardware aging, its data is automatically removed to avoid global control deviations caused by single-point failures.

[0040] Step S250: Determine whether the standard deviation of the clock time of the sensors at multiple detection points is lower than a first threshold and higher than a preset second threshold.

[0041] In this embodiment, the first threshold can be set to 200 microseconds; exceeding this value indicates severe clock desynchronization. The second threshold can be set to 30 microseconds; falling below this value is considered acceptable clock synchronization. If the time is between 30 and 200 microseconds, proceed to the next step.

[0042] Step S260: Adjust the clock time of sensors whose standard deviation of clock time is lower than a first threshold and higher than a second threshold, and adjust the clock time of the sensor at the i-th detection point among the multiple detection points after adjustment. , This refers to the clock time of the sensor at the preset master node among multiple detection points. This represents the clock time of the sensor at the i-th detection point before adjustment, where n is the number of detection points. Let be the standard deviation of the sensor clock time at the i-th detection point.

[0043] In this embodiment, the above formula uses weighted averages based on the inverse of the error variance to ensure that the high-precision master node dominates the synchronization process while suppressing interference from low-precision nodes. In actual testing on an automotive welding line, the clock synchronization accuracy was significantly improved after calibration, meeting the requirements for high-precision motion control. Furthermore, only the clock times of sensors with a standard deviation below a first threshold and above a second threshold are adjusted, reducing network bandwidth usage and significantly lowering the sensor network load in smart factory scenarios.

[0044] According to the technical solution of this embodiment, a high-precision and high-reliability time synchronization solution is provided for multi-sensor collaborative control in intelligent production scenarios, which is especially suitable for high-cycle and high-precision assembly scenarios in new energy vehicle manufacturing.

[0045] like Figure 3 As shown, another embodiment of the present invention provides an intelligent control method for industrial production under complex working conditions. Compared with the aforementioned embodiments, the environmental parameters of the vehicle production environment in this embodiment include the welding current timing signal of the welding electrode; step S130 includes:

[0046] Step S310: Calculate the fluctuation amplitude of the welding current timing signal.

[0047] Specifically, this includes: (1) Calculating the angular frequency of the welding current timing signal based on the frequency of the current welding power source.

[0048] (2) Calculate the phase angle of the welding current timing signal based on the zero-crossing point of the waveform.

[0049] (3) Calculate the fluctuation amplitude of the welding current timing signal based on the angular frequency and phase angle of the welding current timing signal. , This indicates the welding current timing signal. Indicates time, This indicates the preset base current value. This represents the angular frequency of the welding current timing signal. This represents the phase angle of the welding current timing signal. This is a small constant set according to the welding current, and its value is usually between 0.000001 and 0.0001.

[0050] In this embodiment, a mathematical model of the angular frequency and phase angle of the welding current timing signal is constructed, and combined with dynamic compensation of the base current value, to achieve high-precision calculation of the current fluctuation amplitude. This model overcomes the limitations of traditional fixed threshold monitoring, can identify minute current fluctuations, and avoids missing early signs of spatter caused by current distortion.

[0051] Step S320: Determine whether the fluctuation amplitude of the welding current timing signal exceeds the preset amplitude.

[0052] Step S330: When the fluctuation amplitude of the welding current timing signal exceeds the preset amplitude, an image of welding spatter at the welding point is acquired at the preset position.

[0053] Step S340: Calculate the spatter intensity based on the welding spatter image.

[0054] Specifically, this includes: (1) acquiring multiple consecutive images of welding spatter and calculating the spatial gradient and color gradient between each pair of adjacent welding spatter images.

[0055] In this embodiment, the motion trajectory of the splashes is captured by the gradient changes of continuous frame images, which can identify micron-sized splash particles.

[0056] (2) Detect the distance between the preset position and the welding point.

[0057] (3) Calculate the splash intensity , The number of consecutive images of welding spatter. This represents the spatial gradient of the k-th welding spatter image relative to the (k+1)-th welding spatter image in a series of consecutive welding spatter images. Let be the color gradient of the k-th welding spatter image relative to the (k+1)-th welding spatter image, and let e be the base of the natural logarithm function. d is the preset attenuation factor, and d is the distance between the preset position and the welding point.

[0058] In this embodiment, an attenuation factor is introduced to correct the brightness attenuation of the splash image and eliminate misjudgments caused by changes in detection distance.

[0059] Step S350: Determine whether the splash intensity is higher than the preset intensity.

[0060] Step S360: If the splash intensity is higher than the preset intensity, it is determined that there is an abnormal working condition.

[0061] Step S140 includes: adjusting the pressure of the welding electrode to reduce spatter intensity.

[0062] Specifically, this includes: (1) setting spatter sensitivity factors according to the welding material.

[0063] Furthermore, real-time surface condition images of the welding area are acquired, and the oxide layer thickness and micro-roughness of the welding material surface are identified based on the surface condition images. The welding current is monitored in real time, and the spatter sensitivity factor is dynamically adjusted according to the oxide layer thickness, micro-roughness, and welding current. ,in As a baseline splash sensitivity factor, , To preset weights, The thickness of the oxide layer on the surface of the welding material. For reference thickness, The micro-roughness of the welding material surface. For reference roughness, As the reference current, The slope of the welding current rise time is used. The oxide layer thickness and roughness are obtained in real time through image recognition. These are key but often overlooked physical factors affecting spatter. The originally fixed spatter sensitivity factor is transformed into a function coupled with the material surface state, which significantly improves the control accuracy. The current change rate is introduced to reflect the "transient response under working conditions".

[0064] (2) Calculate the splash suppression pressure based on the splash sensitivity factor and splash intensity. , As a splash-sensitive factor, The intensity of the splash.

[0065] (3) Set the thermal compensation factor according to the expansion coefficient and elastic modulus of the welding material and the volume of the welding electrode.

[0066] (4) Calculate the thermal compensation pressure based on the thermal compensation factor and welding temperature. , The coefficient of thermal expansion of the welding material. The elastic modulus of the welding material, For the volume of the welding electrode, Equivalent to a heat compensation factor, Indicates multiplication. Let be the welding temperature, and e be the base of the natural logarithm function. The softening coefficient of the welding material. The room temperature of the vehicle manufacturing environment.

[0067] (5) Adjust the pressure of the welding electrode , This is the base pressure for the welding electrode.

[0068] In this embodiment, the electrode pressure is dynamically adjusted by a spatter-sensitive factor, which can significantly reduce welding spatter. By combining the material's coefficient of thermal expansion and elastic modulus to increase the thermal compensation pressure, the impact of electrode deformation caused by welding thermal deformation on the welding process can be compensated in real time.

[0069] According to the technical solution of this embodiment, by integrating welding current timing signal analysis and spatter dynamic monitoring, a precise identification and closed-loop control mechanism for abnormal conditions in the welding process is constructed, which significantly improves the real-time performance and adaptability of welding quality control.

[0070] like Figure 4 As shown, another embodiment of the present invention provides an intelligent control method for industrial production under complex working conditions. Compared with the aforementioned embodiments, the environmental parameters of the vehicle production environment in this embodiment include the assembly force feedback data of the assembly robotic arm; step S130 includes:

[0071] Step S410: Determine whether the assembly force feedback data of the assembly robot arm is higher than a preset threshold.

[0072] Step S420: When the assembly force feedback data of the assembly robot arm is higher than the preset threshold, it is determined that there is an abnormal working condition.

[0073] Step S140 includes: adjusting the stiffness matrix of the assembly robot arm to reduce the assembly force feedback data of the assembly robot arm.

[0074] In this embodiment, further, when adjusting the stiffness matrix of the assembly robot arm, a digital twin model of the component to be assembled can be obtained, and based on this digital twin model, the expected thermal deformation of the component at the assembly position under the current ambient temperature and historical welding heat input conditions can be predicted. According to the expected thermal deformation, the basic stiffness matrix of the assembly robot arm is pre-adjusted. Simultaneously, abnormal working condition records for the same vehicle model and assembly point are queried from the historical production database. If the point has experienced more than a threshold number of assembly force exceedance events within a preset time period, the damping component in the stiffness matrix is ​​automatically increased before the current assembly begins to suppress transient impacts. In this embodiment, the thermal impact information of the upstream welding station is fed forward to the downstream assembly station. Based on the stiffness pre-adjustment strategy of the digital twin, the structural deformation trend is predicted, and the stiffness is adjusted in advance. An abnormal mode memory function is also introduced: when a certain vehicle model / welding point has frequently experienced high assembly forces, the system automatically increases the initial stiffness tolerance at that position.

[0075] In this embodiment, when abnormal assembly force is detected, the joint stiffness of the assembly robot arm can be dynamically increased to suppress the transmission of impact load.

[0076] Specifically, this includes: (1) determining the basic stiffness matrix and stiffness increment based on the assembly materials.

[0077] (2) Set the compensation factor according to the welding temperature.

[0078] In this embodiment, under the high temperature of welding, the stiffness loss is compensated by a compensation factor, which can stabilize the assembly positioning accuracy.

[0079] (3) Adjust the stiffness matrix of the assembly robot arm , The basic stiffness matrix is... As a preset adjustment factor, The preset reference temperature difference Given the thermal relaxation coefficient of the welding material, The welding temperature is... The preset base temperature, For the stiffness increment, The function is the hyperbolic tangent function. The function is a hyperbolic cosine function. This represents the maximum force exerted on the assembly robot arm. This refers to the assembly force feedback data of the assembly robot arm. Indicates multiplication.

[0080] In this embodiment, the temperature dependence of the coefficient of linear expansion and elastic modulus of different materials (such as aluminum alloys and high-strength steel) is experimentally calibrated to compensate for the stiffness attenuation caused by welding heat input. A hyperbolic tangent function is used to smoothly transition the stiffness increment, avoiding mechanical vibration caused by abrupt stiffness changes.

[0081] According to the technical solution of this embodiment, by constructing a dynamic adjustment mechanism for the stiffness matrix driven by assembly force feedback, the precise control of force position and the improvement of anti-interference ability in the assembly process of the robotic arm are realized, and the assembly quality and equipment reliability under complex working conditions are significantly optimized.

[0082] like Figure 5 As shown, one embodiment of the present invention provides an intelligent control system for industrial production under complex working conditions, used in vehicle production, comprising:

[0083] The parameter acquisition module 510 collects environmental parameters of the vehicle production environment through sensors deployed at multiple detection points in the vehicle production environment.

[0084] The parameter alignment module 520 aligns the environmental parameters of the vehicle production environment of the sensors at multiple detection points according to a preset method.

[0085] In this embodiment, a preset spatiotemporal alignment algorithm is used to solve the problem of spatiotemporal misalignment of data from different detection points in traditional sensor networks due to sampling frequency and transmission delay, thereby achieving high-precision spatiotemporal registration of environmental parameters.

[0086] The operating condition analysis module 530 determines whether there are any abnormal operating conditions based on the environmental parameters of the vehicle production environment.

[0087] In this embodiment, hidden anomalies under complex working conditions can be identified based on multi-parameter correlation analysis.

[0088] The parameter adjustment module 540 adjusts the environmental parameters of the vehicle production environment to eliminate abnormal operating conditions when such conditions exist, and predicts the maintenance cycle of the vehicle production environment based on the environmental parameters when no abnormal operating conditions exist.

[0089] In this embodiment, the environmental stability index of the vehicle production environment can be calculated based on parameters such as temperature fluctuation rate, vibration acceleration change, and humidity deviation. When the environmental stability index is too low, the operation and maintenance cycle calculation is triggered. ,in, As the baseline maintenance cycle, , For the preset weights, The aforementioned environmental stability index can be obtained by assigning different weights to each parameter, such as temperature fluctuation rate, vibration acceleration change, and humidity deviation, based on historical experience, and then summing them together. The number of types of parameters such as temperature fluctuation rate, vibration acceleration change, and humidity deviation. For the j-th type parameter The deviation from normal values. Normal values ​​and baseline maintenance cycles are environmental parameters or maintenance cycles corresponding to normal vehicle production or production environment parameters or maintenance cycles obtained from historical experience. This embodiment can reasonably assess the operation and maintenance cycle of the vehicle production environment and prompt timely maintenance of the production environment.

[0090] According to the technical solution of this embodiment, by constructing a closed-loop architecture of "perception-decision-execution", the optimization of work production management is realized, which is conducive to ensuring production continuity and provides an innovative solution for complex industrial process control in intelligent manufacturing scenarios, with significant economic benefits and industrial promotion value.

[0091] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0092] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0093] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0094] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0095] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. Intelligent control methods for industrial production under complex operating conditions, applied to vehicle production, including: Environmental parameters of the vehicle production environment are collected by sensors deployed at multiple detection points in the vehicle production environment. The environmental parameters of the vehicle production environment at the sensors at the multiple detection points are aligned according to a preset method. Based on the environmental parameters of the vehicle production environment, determine whether there are any abnormal operating conditions. When the abnormal operating condition exists, the environmental parameters of the vehicle production environment are adjusted to eliminate the abnormal operating condition. When the abnormal operating conditions do not currently exist, the maintenance cycle of the vehicle production environment is predicted based on the environmental parameters of the vehicle production environment.

2. The intelligent control method for industrial production under complex working conditions according to claim 1, wherein, Aligning the environmental parameters of the vehicle production environment at the sensors at the multiple detection points according to a preset method, including: Collect the clock time of the sensors at the multiple detection points; Calculate the standard deviation of the clock time of the sensors at the multiple detection points; Determine whether the standard deviation of the clock time of the sensors at the multiple detection points is higher than a preset first threshold; From the environmental parameters of the vehicle production environment collected by the sensors at the multiple detection points, the environmental parameters of the vehicle production environment collected by the sensors whose standard deviation of clock time is higher than the first threshold are removed. Determine whether the standard deviation of the clock time of the sensors at the multiple detection points is lower than the first threshold and higher than the preset second threshold; The clock times of sensors whose standard deviation is below the first threshold and above the second threshold are adjusted, and the adjusted clock time is the clock time of the sensor at the i-th detection point among the plurality of detection points. , This refers to the clock time of the sensor at the preset master node among the multiple detection points. The clock time of the sensor at the i-th detection point before adjustment is given, where n is the number of detection points. Let be the standard deviation of the clock time of the sensor at the i-th detection point.

3. The intelligent control method for industrial production under complex working conditions according to claim 1, wherein, The environmental parameters of the vehicle production environment include the welding current timing signal of the welding electrode; Based on the environmental parameters of the vehicle production environment, determine whether there are any abnormal operating conditions, including: Calculate the fluctuation amplitude of the welding current timing signal; Determine whether the fluctuation amplitude of the welding current timing signal exceeds a preset amplitude; When the fluctuation amplitude of the welding current timing signal exceeds the preset amplitude, an image of welding spatter at the welding point is acquired at a preset position; Calculate the spatter intensity based on the weld spatter image; Determine whether the splash intensity is higher than a preset intensity; If the splash intensity is higher than a preset intensity, it is determined that the abnormal operating condition exists. Adjusting the environmental parameters of the vehicle production environment to eliminate the abnormal operating conditions includes: Adjust the pressure of the welding electrode to reduce the spatter intensity.

4. The intelligent control method for industrial production under complex working conditions according to claim 3, wherein, Calculating the fluctuation amplitude of the welding current timing signal includes: Calculate the angular frequency of the welding current timing signal based on the frequency of the current welding power source. Calculate the phase angle of the welding current timing signal based on the zero-crossing point of the waveform; The fluctuation amplitude of the welding current timing signal is calculated based on the angular frequency and phase angle of the welding current timing signal.

5. The intelligent control method for industrial production under complex working conditions according to claim 3, wherein, Based on the weld spatter image, the spatter intensity is calculated, including: Acquire multiple consecutive images of the welding spatter, and calculate the spatial gradient and color gradient between each pair of adjacent welding spatter images; Detect the distance between the preset position and the weld joint; The spatter intensity is calculated based on the spatial and color gradients between each pair of adjacent welding spatter images and the distance between the preset position and the welding point.

6. The intelligent control method for industrial production under complex working conditions according to claim 3, wherein, Adjusting the pressure of the welding electrode to reduce the spatter intensity includes: Set the spatter sensitivity factor according to the welding material; Calculate the splash suppression pressure based on the splash sensitivity factor and the splash intensity. , For the splash-sensitive factor, The splash intensity; A thermal compensation factor is set based on the coefficient of thermal expansion and elastic modulus of the welding material and the volume of the welding electrode; Calculate the thermal compensation pressure based on the aforementioned thermal compensation factor and welding temperature. , The coefficient of thermal expansion of the welding material is given. The elastic modulus of the welding material is given. The volume of the welding electrode. Equivalent to the aforementioned thermal compensation factor, Indicates multiplication. Let e ​​be the welding temperature, and e be the base of the natural logarithm function. The softening coefficient of the welding material is given. The room temperature of the vehicle production environment; Adjust the pressure of the welding electrode , This is the base pressure of the welding electrode.

7. The intelligent control method for industrial production under complex working conditions according to claim 1, wherein, The environmental parameters of the vehicle production environment include the assembly force feedback data of the assembly robotic arm; Based on the environmental parameters of the vehicle production environment, determine whether there are any abnormal operating conditions, including: Determine whether the assembly force feedback data of the assembly robot arm is higher than a preset threshold; When the assembly force feedback data of the assembly robot arm is higher than the preset threshold, it is determined that the abnormal working condition exists. Adjusting the environmental parameters of the vehicle production environment to eliminate the abnormal operating conditions includes: Adjust the stiffness matrix of the assembly robot arm to reduce the assembly force feedback data of the assembly robot arm.

8. The intelligent control method for industrial production under complex working conditions according to claim 7, wherein, Adjusting the stiffness matrix of the assembly robot arm includes: Determine the basic stiffness matrix and stiffness increment based on the assembly materials; Set the compensation factor according to the welding temperature; Adjusting the stiffness matrix of the assembly robot arm , The basic stiffness matrix is... As a preset adjustment factor, The preset reference temperature difference Given the thermal relaxation coefficient of the welding material, The welding temperature is... The preset base temperature, For the stiffness increment, The function is the hyperbolic tangent function. The function is a hyperbolic cosine function. This represents the maximum force exerted on the assembly robot arm. This refers to the assembly force feedback data of the assembly robot arm. Indicates multiplication.

9. Intelligent control systems for industrial production under complex operating conditions, used in vehicle production, including: The parameter acquisition module collects environmental parameters of the vehicle production environment through sensors deployed at multiple detection points in the vehicle production environment; The parameter alignment module aligns the environmental parameters of the vehicle production environment of the sensors at the multiple detection points according to a preset method. The operating condition analysis module determines whether there are any abnormal operating conditions based on the environmental parameters of the vehicle production environment. The parameter adjustment module adjusts the environmental parameters of the vehicle production environment to eliminate the abnormal operating condition when the abnormal operating condition exists, and predicts the maintenance cycle of the vehicle production environment based on the environmental parameters of the vehicle production environment when the abnormal operating condition does not exist.

Images