Energy-saving control method and system of automatic optical inspection machine

Abstract

The application provides an energy-saving control method and system of an automatic optical inspection machine, and relates to the field of industrial production.The method comprises the following steps: obtaining a task request of a user, determining the task complexity of each automatic optical inspection machine contained in the task request according to a preset task classification rule, performing initial configuration of each operation parameter of the automatic optical inspection machine according to the task complexity, determining the minimum operation power meeting the task request according to each operation parameter, obtaining each equipment state parameter of the automatic optical inspection machine under the initial configuration, taking the minimum operation power as an adjustment benchmark, and adjusting the operation parameter according to the equipment state parameter.The application improves the operation efficiency and energy utilization rate of the AOI machine, and provides an effective solution for intelligent control of the AOI machine operation.

Description

Technical Field

[0001] This invention relates to the field of industrial production, and in particular to an energy-saving control method and system for an automatic optical inspection machine. Background Technology

[0002] In modern manufacturing, Automated Optical Inspection (AOI) machines, which utilize automated inspection technology, are devices that detect common defects encountered in industrial production based on optical principles. AOI machines can effectively improve production efficiency and product quality, and their technological development is directly related to the level of intelligence in industrial production and the efficiency of resource utilization. Although significant progress has been made in the development of AOI machines, existing AOI machines still reveal deep-seated shortcomings when dealing with diverse production needs. Many current solutions often neglect the dynamic matching between AOI machine operation and task characteristics, resulting in inflexible resource allocation, especially in energy management, where problems such as excessive consumption or inefficiency are common. This limitation not only increases operating costs but also contradicts the sustainable development goals of green manufacturing.

[0003] Therefore, how to switch operating power based on task complexity during AOI machine operation is an important issue that the industry urgently needs to address. Summary of the Invention

[0004] In view of this, the present invention proposes an energy-saving control method and system for an automatic optical inspection machine, thereby solving the problem that AOI machines are unable to meet diverse production needs.

[0005] The technical solution of this invention is implemented as follows:

[0006] According to a first aspect, embodiments of the present invention provide an energy-saving control method for an automatic optical inspection machine, the method comprising:

[0007] The task request of the user is obtained, and the task complexity of each automatic optical inspection machine in the task request is determined according to the preset task classification rules. The preset task classification rules include several preset influence items and the influence weight of each preset influence item. Each preset influence item has a maximum preset threshold and a minimum preset threshold. The minimum and maximum preset thresholds define the preset threshold range of the preset influence item.

[0008] Based on the complexity of the task, perform the initial configuration of various operating parameters of the automatic optical inspection machine;

[0009] Determine the minimum operating power required to meet the task requirements based on various operating parameters, obtain the various equipment status parameters of the automatic optical inspection machine under the initial configuration, use the minimum operating power as the adjustment benchmark, and adjust the operating parameters according to the equipment status parameters.

[0010] In conjunction with the first aspect, in the first embodiment of the first aspect, the step of determining the minimum operating power to meet the task request based on various operating parameters, obtaining various equipment status parameters of the automatic optical inspection machine under the initial configuration, using the minimum operating power as an adjustment benchmark, and adjusting the operating parameters according to the equipment status parameters specifically includes:

[0011] The minimum operating power, power adjustment range, and optimal operating power are determined based on various operating parameters; the value of the optimal operating power exceeds the value of the minimum operating power.

[0012] Acquire the various equipment status parameters of the automated optical inspection machine under its initial configuration;

[0013] The device status parameters are compared with the corresponding preset device parameters to obtain the comparison results;

[0014] Based on the comparison results, determine whether the operating parameters need to be adjusted. If it is determined that the operating parameters need to be adjusted, use the lowest operating power as the adjustment benchmark and the power adjustment range as the step size to iteratively adjust the operating parameters until it is determined that the operating parameters do not need to be adjusted based on the comparison results.

[0015] In conjunction with the first aspect, in a second embodiment of the first aspect, the method further includes:

[0016] The system acquires control signal frequency and power fluctuation data of the automated optical inspection machine under adjusted operating parameters, and generates a resource configuration scheme for the automated optical inspection machine based on the control signal frequency and power fluctuation data.

[0017] In conjunction with the second embodiment of the first aspect, and in the third embodiment of the first aspect, the step of acquiring the control signal frequency and power fluctuation data of the automatic optical inspection machine operating under adjusted operating parameters, and generating a resource allocation scheme for the automatic optical inspection machine based on the control signal frequency and power fluctuation data, specifically includes:

[0018] Acquire control signal frequency and power fluctuation data of the automatic optical inspection machine under adjusted operating parameters;

[0019] Determine the first influencing factor of the control signal frequency and the second influencing factor of the power fluctuation data;

[0020] The energy consumption level of the simulated automatic optical inspection machine under the resource allocation scheme is measured. If the energy consumption level exceeds the preset energy-saving standard, the resource allocation scheme is adjusted. The preset energy-saving standard is determined based on the complexity of the task.

[0021] In conjunction with the third implementation of the first aspect, in the fourth implementation of the first aspect, the adjustment of the resource allocation scheme is based on the degree of influence of the first influence factor and the second influence factor, and the first influence factor and the second influence factor are prioritized according to the degree of influence, and the priority has a mapping relationship with the adjustment order and the adjustment range.

[0022] In conjunction with the first aspect, in the fifth embodiment of the first aspect, the step of obtaining the user's task request and determining the task complexity of each automatic optical inspection machine included in the task request according to a preset task classification rule specifically includes:

[0023] Obtain the user's task request and extract the task description information from the task request;

[0024] The equipment information and complexity features are filtered out from the task description information, and a mapping relationship is established between each piece of equipment information and its corresponding complexity feature; each piece of equipment information corresponds to an automatic optical inspection machine.

[0025] Based on the preset task classification rules, the complexity characteristics of each piece of equipment information are matched with preset influencing factors to obtain the task complexity of the automatic optical inspection machine corresponding to each piece of equipment information.

[0026] In conjunction with the fifth embodiment of the first aspect, and in the sixth embodiment of the first aspect, the step of matching the complexity characteristics of each piece of equipment information with preset influence items according to preset task classification rules to obtain the task complexity of the automatic optical inspection machine corresponding to each piece of equipment information specifically includes:

[0027] According to the preset task classification rules, each complexity feature is matched with the corresponding preset influence item; based on the correlation between the feature value of the complexity feature and the preset threshold range of the preset influence item, the feature matching score of each complexity feature is determined.

[0028] The influence score of each complexity feature is obtained based on the feature matching score of each complexity feature and the influence weight of the preset influence item.

[0029] By aggregating the influence scores of all complexity features for each piece of equipment used, the task complexity of the corresponding automated optical inspection machine can be obtained.

[0030] In conjunction with the sixth embodiment of the first aspect, and the seventh embodiment of the first aspect, the initial configuration of various operating parameters of the automatic optical inspection machine according to the complexity of the task specifically includes:

[0031] Features with complexity whose feature matching scores exceed a preset score are marked as priority features;

[0032] Preset control strategies are retrieved from the preset strategy library based on priority configuration features and task complexity; the preset strategy library stores several preset control strategies, each with corresponding preset parameters.

[0033] Based on the preset parameters in the preset control strategy, the initial configuration of various operating parameters of the automatic optical inspection machine is performed.

[0034] In conjunction with the seventh embodiment of the first aspect, and in the eighth embodiment of the first aspect, the initial configuration of various operating parameters of the automatic optical inspection machine according to the complexity of the task further includes:

[0035] If the number of priority configuration features exceeds the preset number, the retrieved preset control strategy is upgraded to obtain an updated preset control strategy.

[0036] According to a second aspect, embodiments of the present invention provide an energy-saving control system for an automatic optical inspection machine, the system comprising:

[0037] The task parsing module is used to obtain the user's task request and determine the task complexity of each automatic optical inspection machine included in the task request according to the preset task classification rules. The preset task classification rules include several preset influence items and the influence weight of each preset influence item. Each preset influence item has a maximum preset threshold and a minimum preset threshold. The minimum and maximum preset thresholds define the preset threshold range of the preset influence item.

[0038] The initial configuration module is used to configure the various operating parameters of the automatic optical inspection machine according to the complexity of the task.

[0039] The energy-saving control module is used to determine the minimum operating power required to meet the task request based on various operating parameters, acquire various equipment status parameters of the automatic optical inspection machine under the initial configuration, use the minimum operating power as the adjustment benchmark, and adjust the operating parameters according to the equipment status parameters.

[0040] The energy-saving control method and system for the automatic optical inspection machine of the present invention have the following advantages over the prior art:

[0041] 1. By parsing the task requests sent by users, the complexity of each AOI machine in the task request is determined based on the preset task classification rules. This provides a reference for the initial configuration of subsequent operating parameters. The initially configured operating parameters need to be able to adapt to the task complexity to ensure that the AOI machine can successfully complete the user's task request and then manage the AOI according to the task request. At the same time, different task complexities have different requirements for AOI machine performance. The task complexity is quantified by the preset influencing items and influence weights in the preset task classification rules to achieve accurate identification of task requests and lay the foundation for the adjustment of subsequent operating parameters.

[0042] 2. The AOI machine's various operating parameters are initially configured using preset parameters in the preset control strategy. This preset control strategy is determined based on priority configuration characteristics and task complexity, ensuring that the initial configuration strategy closely matches production needs. When the task complexity is high, a high-performance (or high-resource-consumption) configuration strategy can be selected to meet production requirements. Conversely, when the task complexity is low, a low-power (or energy-saving) configuration strategy can be selected to reduce resource consumption, extend equipment lifespan, and provide diverse options for equipment operation, effectively improving equipment stability.

[0043] 3. Determine the minimum operating power required to meet the task request by analyzing various operating parameters. Then, obtain the various equipment status parameters of the AOI machine under the initial configuration. Use the minimum operating power as the adjustment benchmark and adjust the operating parameters according to the equipment status parameters. The minimum operating power is the minimum value of the AOI machine's working power when meeting the task request. Using the minimum operating power as the adjustment benchmark can avoid focusing only on energy saving while ignoring production needs during the adjustment process. Setting the adjustment of operating parameters as a dynamic adjustment process, through real-time monitoring and feedback, ensures that the power adjustment can be truly implemented in equipment operation, ensuring that the equipment remains stable even in complex operating environments. This not only improves the response speed of the adjustment, but also reduces equipment wear and tear and extends service life through precise adjustment, improving the operating efficiency and energy utilization of the AOI machine, providing an effective solution for the intelligent control of AOI machine operation. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1This is one of the flowcharts illustrating the energy-saving control method of the automatic optical inspection machine of the present invention;

[0046] Figure 2 This is a second schematic flowchart of the energy-saving control method for the automatic optical inspection machine of the present invention;

[0047] Figure 3 This is the third flowchart illustrating the energy-saving control method of the automatic optical inspection machine of the present invention;

[0048] Figure 4 This is a schematic diagram of the energy-saving control system of the automatic optical inspection machine of the present invention. Detailed Implementation

[0049] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0050] In modern manufacturing, AOI (Automated Inspection) machines, which utilize optical principles, are devices that detect common defects encountered in industrial production. AOI machines effectively improve production efficiency and product quality, and their technological development is directly related to the level of intelligence and resource utilization efficiency in industrial production. Although significant progress has been made in the development of AOI machines, existing AOI machines still reveal deep-seated shortcomings when dealing with diverse production needs. Many current solutions often neglect the dynamic matching between AOI machine operation and task characteristics, resulting in inflexible resource allocation, especially in energy management, where problems such as excessive consumption or inefficiency are common. This limitation not only increases operating costs but also contradicts the sustainable development goals of green manufacturing.

[0051] Specifically, AOI machines face the challenge of achieving refined management based on task requirements in practical applications. This is due to the variability in task complexity, with different tasks having vastly different performance demands on the equipment. Existing technologies often fail to accurately identify and adapt to these changes, leading to indiscriminate energy use. Furthermore, this inability to accurately identify and adapt to these changes directly impacts the precision of power regulation, making it difficult for AOI machines to intelligently switch between high and low load scenarios, resulting in energy waste or poor detection results. It can be seen that these two factors are closely linked: the dynamic changes in task complexity are the root cause, while insufficient adaptability in power regulation is its direct manifestation. Together, they constitute the core obstacle for AOI machines to meet diverse production needs.

[0052] In conclusion, how to switch operating power based on task complexity during AOI machine operation is an important issue that the industry urgently needs to address.

[0053] The energy-saving control method for automatic optical inspection machines provided in this manual aims to achieve intelligent selection and dynamic adjustment of power levels based on the complexity of the task, thereby improving the operating efficiency and energy utilization of AOI machines and providing an effective solution for the intelligent control of AOI machine operation.

[0054] Please see Figure 1 , Figure 1 This is a flowchart illustrating the energy-saving control method of the automatic optical inspection machine of the present invention, which may include the following steps:

[0055] S101. Obtain the user's task request and determine the task complexity of each AOI machine included in the task request according to the preset task classification rules.

[0056] User-sent task requests can be presented in various forms such as text, forms, images, and structured data. After obtaining the task request, the various forms of task requests are parsed to extract features describing the complexity of the production task, i.e., complexity features are extracted. For example, pre-trained form segmentation models, text extraction models, and semantic analysis models are used for the above processing.

[0057] There are no restrictions on the specific form of complexity feature extraction, as long as the electronic device can acquire the complexity feature.

[0058] The task request issued to the AOI machine contains multiple task description details, such as start time, equipment number, operator number, and task content. These descriptions directly affect the assessment of task complexity. In this embodiment, these task descriptions are analyzed to extract features describing the complexity of the production task, such as the object to be inspected, defect type, environmental conditions (e.g., temperature), and required inspection accuracy. It should be noted that a single task request may contain production tasks from multiple AOI machines; therefore, a mapping relationship between the equipment used and the corresponding complexity features is established during extraction.

[0059] Determining the appropriate task complexity for each AOI machine can provide a reference for the initial configuration of subsequent operating parameters. Different task complexities correspond to different initial configuration strategies. The initial configuration operating parameters need to be able to adapt to the task complexity to ensure that the AOI machine can successfully complete the user's task request and then manage the AOI based on the task request. At the same time, different task complexities have different performance requirements for the AOI machine. By quantifying the task complexity through preset influencing items and influencing weights in the preset task classification rules, the task request can be accurately identified, laying the foundation for the adjustment of subsequent operating parameters.

[0060] Specifically, step S101 includes:

[0061] S1011. Obtain the user's task request and extract the task description information from the task request. The task description information includes the specific information such as the start time, device number, operator number, and task objective mentioned above.

[0062] S1012. Filter out the equipment information and complexity features from the task description information, and establish a mapping relationship between each piece of equipment information and its corresponding complexity feature. Each piece of equipment information corresponds to one AOI machine.

[0063] The equipment information includes information such as the equipment number. This establishes a mapping relationship between the equipment number and the corresponding complexity characteristics. For example, an AOI machine numbered 1 is mapped to the corresponding operator number, inspection object, defect type, environmental conditions, and inspection accuracy requirements. When the task description information contains multiple pieces of equipment information, meaning that the production task requires the participation of multiple AOI machines, it is understandable that a mapping relationship will be established between each piece of equipment information and the corresponding complexity characteristics.

[0064] S1013. According to the preset task classification rules, match the complexity features of each piece of equipment information with preset influence items to obtain the task complexity of the AOI machine corresponding to each piece of equipment information. The preset task classification rules include several preset influence items and the influence weight of each preset influence item. Each preset influence item has a preset threshold range, that is, each preset influence item has a maximum preset threshold and a minimum preset threshold, and the minimum and maximum preset thresholds constitute the preset threshold range.

[0065] In this embodiment, several preset influence items are pre-set, and each preset influence item is assigned a corresponding influence weight. Subsequently, the complexity features are matched with the preset influence items to determine the task complexity of the AOI machine.

[0066] That is, step S1013 more specifically includes:

[0067] According to the preset task classification rules, each complexity feature is matched with the corresponding preset influence item. Based on the correlation between the feature value of the complexity feature and the preset threshold range of the preset influence item, the feature matching score of each complexity feature is determined. Then, based on the feature matching score of each complexity feature and the influence weight of the preset influence item, the influence score of each complexity feature is obtained. Finally, the influence scores of all complexity features of each device information are collected to obtain the task complexity of the corresponding AOI machine.

[0068] Preferably, the Fusion tool can be used to perform feature matching scores and weighted calculations of influencing weights to reflect the complexity of the task, obtain the task complexity level, and quantify the task complexity level.

[0069] The quantified task complexity can also be further classified into specific levels. That is, the complexity level of the task is obtained based on the quantified value of the task complexity, which ensures the objective assessment of the task complexity and improves the operating efficiency and reliability of the AOI machine.

[0070] S102. Based on the complexity of the task, perform the initial configuration of various operating parameters of the AOI machine.

[0071] Initial parameter configuration based on task complexity ensures that the initial device configuration strategy closely aligns with production needs. For high-complexity tasks, a high-performance (or high-resource-consumption) configuration strategy can be chosen to meet production demands. Conversely, for lower-complexity tasks, a low-power (or energy-saving) configuration strategy can be selected to reduce resource consumption and extend device lifespan. This flexible configuration approach provides diverse options for device operation and effectively improves operational stability, especially crucial in highly complex task scenarios where proper configuration is paramount.

[0072] Specifically, step S102 includes:

[0073] S1021. Mark the complexity features whose feature matching scores exceed the preset scores as priority configuration features.

[0074] When the value of a certain complexity feature exceeds the maximum preset threshold of the corresponding preset influence item, the feature matching score of that complexity feature will exceed the preset score, and these complexity features will be marked as priority configuration features.

[0075] S1022. Retrieve a preset control strategy from the preset strategy library based on priority configuration features and task complexity. The preset strategy library stores several preset control strategies, each with corresponding preset parameters.

[0076] The retrieval process can be achieved through database filtering tools, which can quickly match relevant data based on priority configuration features and task complexity, ensuring the relevance of subsequent analysis. Among these, priority configuration features can serve as the core focus of the filtering, i.e., matching process, selecting a better preset control strategy from preset control strategies of similar style.

[0077] Specifically, for example, when the priority configuration features are detection accuracy requirements and environmental conditions (ambient temperature) requirements, and the task complexity is medium, the configuration strategy for the preset parameters of preset control strategy A is a dual-color ring light illumination mode (brightness 70%), motion control accuracy of ±2μm, high priority for image processing memory allocation, and full-speed operation of the cooling fan; as another example, when the priority configuration features are the detection object and defect type, and the task complexity is medium, the configuration strategy for the preset parameters of preset control strategy B is a multi-spectral illumination mode (brightness 100%), motion control accuracy of ±5μm, medium priority for image processing memory allocation, and medium-speed operation of the cooling fan; as yet another example, for the case with no priority configuration features and medium task complexity, the configuration strategy for the preset parameters of preset control strategy C is a dual-color ring light illumination mode (brightness 70%), motion control accuracy of ±5μm, medium priority for image processing memory allocation, and medium-speed operation of the cooling fan.

[0078] S1023. Based on the preset parameters in the preset control strategy, perform the initial configuration of various operating parameters of the AOI machine.

[0079] With the task complexity assessed for each AOI machine, a preset control policy will be retrieved from the preset policy library based on the number of priority configuration features. That is, the number serves as the matching benchmark with each preset control policy stored in the preset policy library.

[0080] Retrieving the performance parameter dataset corresponding to the task complexity level from the equipment performance database is particularly important. Each preset control strategy has corresponding preset parameters, which can be understood as the performance parameters of the AOI machine during operation. These preset parameters may include key parameters such as lighting mode, motion control accuracy, memory capacity, and heat dissipation capacity. Taking AOI machine number 1 as an example, assuming its assessed task complexity level is high, the preset parameters corresponding to its matched preset control strategy might be a multispectral lighting mode (100% brightness), motion control accuracy of ±2μm, memory capacity of 16GB, heat dissipation capacity of 8000 BTU per hour, power output of 180W, and vibration frequency of 50Hz. These parameters directly reflect the equipment's operational requirements under highly complex tasks.

[0081] In this embodiment, step S1022 may further include the following steps:

[0082] If the number of priority configuration features exceeds the preset number, the retrieved preset control strategy is upgraded to obtain an updated preset control strategy.

[0083] During the process of retrieving the preset control strategy, the number of priority configuration features is the core focus of the screening process. When the number of priority configuration features exceeds the preset number, it means that in order to meet the production needs of the actual task, the AOI machine needs to run under a state of higher resource consumption. Therefore, the preset control strategy will be upgraded to ensure that the user's task request can be completed.

[0084] S103. Determine the minimum operating power to meet the task request based on various operating parameters, obtain various equipment status parameters of the AOI machine under the initial configuration, use the minimum operating power as an adjustment benchmark (a lower limit benchmark), and adjust the operating parameters according to the equipment status parameters. The equipment status parameters include parameters such as equipment temperature, load occupancy rate, and runtime, which directly reflect the actual status of the AOI machine.

[0085] For example, the temperature of an AOI machine reflects its operating status; excessively high temperatures may lead to performance degradation. Load utilization indicates resource usage; high load may increase the risk of failure. Running time is related to the degree of equipment fatigue.

[0086] In this embodiment, the minimum operating power is the minimum value of the AOI machine's operating power when the task request is met. Using the minimum operating power as the adjustment benchmark can avoid focusing solely on energy saving while neglecting production needs during the adjustment process. Furthermore, determining the minimum operating power also allows for the determination of a power adjustment range. This range not only characterizes the adjustment magnitude (adjustment step size) of the AOI machine's operating power in a single adjustment but also ensures the stability and reliability of the operating parameter adjustments, guaranteeing that the AOI machine operates in a stable state during adjustment.

[0087] In this embodiment, the rationality of the power adjustment range can be further analyzed for the adjustment of operating parameters. If the AOI machine needs to frequently adjust its operating power according to the power adjustment range, it may mean that the power adjustment range is set too narrowly. In order to optimize the adjustment time and cost of operating parameters, the range of the power adjustment range can be appropriately widened in subsequent adjustment processes, thereby reducing unnecessary adjustments and improving operational stability.

[0088] When acquiring various equipment status parameters of the AOI machine under initial configuration, data can be collected through various sensors, and the data transmitted by the sensors can be uniformly converted into a standard format. For example, temperature data is expressed in degrees Celsius, and load occupancy rate is expressed as a percentage. This forms a standardized set of equipment status parameters, which facilitates subsequent comparison and analysis and ensures data consistency.

[0089] It should be noted that step S103 is a dynamic adjustment process, that is, adjusting the operating parameters and generating new operating parameters, running the corresponding AOI machine with the new operating parameters and continuously acquiring various equipment status parameters, or using the minimum operating power as the adjustment benchmark and adjusting the operating parameters according to the equipment status parameters. In this embodiment, for the updated operating parameters, it will be determined whether dynamic adjustment is needed. Through real-time monitoring and feedback, it is ensured that the power adjustment can be truly implemented in the equipment operation, and that the equipment can remain stable even in complex operating environments. This not only improves the response speed of adjustment, but also reduces equipment wear and extends service life through precise adjustment.

[0090] Please see Figure 2 The method may also include the following steps:

[0091] S201. Obtain the user's task request and determine the task complexity of each AOI machine included in the task request according to the preset task classification rules. Refer to step S101 for details.

[0092] S202. Based on the complexity of the task, perform initial configuration of various operating parameters of the AOI machine. Refer to step S102 for details.

[0093] S2031. Determine the minimum operating power, power adjustment range, and optimal operating power based on various operating parameters, wherein the value of the optimal operating power exceeds the value of the minimum operating power.

[0094] In this embodiment, the optimal operating power to meet the task request will also be determined. When the AOI machine is running at the optimal operating power, no adjustment of the operating parameters is required.

[0095] S2032. Obtain the various device status parameters of the AOI machine under the initial configuration.

[0096] S2033. Compare the device status parameters with the corresponding preset device parameters to obtain the comparison results.

[0097] In this embodiment, a preset device parameter is set for each device status parameter. The preset device parameter can be understood as the limit value of a certain parameter when the AOI machine is running.

[0098] Assuming the temperature threshold for AOI machine number 1 is 80 degrees Celsius, this temperature threshold can be used as the preset device parameter for the device status parameter of temperature. This method of comparison ensures that the status of each dimension can be accurately evaluated, providing a basis for subsequent adjustments. When the value of a device status parameter exceeds the preset device parameter, that device status parameter can be marked as an abnormal parameter.

[0099] S2034. Determine whether the operating parameters need to be adjusted based on the comparison results. If it is determined that the operating parameters need to be adjusted, take the lowest operating power as the adjustment benchmark and the power adjustment range as the step size, and iteratively adjust the operating parameters until it is determined that the operating parameters do not need to be adjusted based on the comparison results, that is, until the comparison results show that no further adjustment is needed.

[0100] Based on the anomaly markers, specific adjustment strategies are formulated in conjunction with the minimum operating power. If the equipment simultaneously experiences both high temperature and load anomalies, the operating power parameters can be adjusted. Each adjustment reduces the current operating power value by the size of a power adjustment range (i.e., the adjustment step size) to reduce the equipment load. This allows for the rapid development of reasonable power configuration schemes under multi-dimensional anomaly conditions, ensuring the safe operation of the equipment.

[0101] Preferably, the dynamic adjustment of operating parameters can also be optimized by combining historical operating data from the AOI machine. For example, if a device has triggered power adjustments multiple times in the past week due to abnormal high temperatures, a more conservative power configuration scheme will be prioritized during the adjustment process to further reduce risk. This adjustment method, driven by historical data, can improve the adaptability and reliability of the equipment.

[0102] Please see Figure 3The method may also include the following steps:

[0103] S301. Obtain the user's task request and determine the task complexity of each AOI machine included in the task request according to the preset task classification rules. Refer to step S101 for details.

[0104] S302. Based on the complexity of the task, perform initial configuration of various operating parameters of the AOI machine. Refer to step S102 for details.

[0105] S303. Determine the minimum operating power to meet the task request based on various operating parameters, obtain the various equipment status parameters of the AOI machine under the initial configuration, use the minimum operating power as the adjustment benchmark, and adjust the operating parameters according to the equipment status parameters. Refer to step S103 for details.

[0106] S304. Obtain the control signal frequency and power fluctuation data of the AOI machine under the adjusted operating parameters, and generate the resource configuration scheme of the AOI machine based on the control signal frequency and power fluctuation data.

[0107] It should be noted that the resource configuration scheme can serve as an initial configuration strategy in certain situations. This allows for the generation of more timely initial configuration strategies using various data collected during the AOI machine's operation, and these strategies are stored in a preset strategy library. This approach provides a more optimized initial configuration strategy for the next startup of AOI machines of the same model. Furthermore, the developed resource configuration scheme aims to balance equipment operation. By comprehensively considering parameters across different dimensions, it enhances the flexibility of the resource configuration scheme, ensuring the high efficiency and stability of equipment operation.

[0108] In this embodiment, the control signal frequency and power fluctuation data during the operation of the AOI machine will also be acquired. The control signal frequency is expressed in Hertz (Hz), and the power fluctuation data is expressed in Watts (watts). For example, the control signal frequency of AOI machine number 1 is 60 Hz, and the power fluctuation data represents a fluctuation range of 5-10 W. Subsequently, the influencing factors of the control signal frequency and power fluctuation data will be analyzed and classified.

[0109] More specifically, step S304 includes:

[0110] S3041. Obtain the control signal frequency and power fluctuation data of the AOI machine under the adjusted operating parameters.

[0111] S3042. Determine the first influencing factor of the control signal frequency and the second influencing factor of the power fluctuation data.

[0112] During the analysis, data analysis is performed on each parameter that may cause changes in the control signal frequency and power fluctuation data. In this embodiment, corresponding influencing factors are determined for the control signal frequency and power fluctuation data, thereby classifying the influencing factors and obtaining the first influencing factor and the second influencing factor. For example, equipment temperature affects power fluctuation, so equipment temperature can be used as the second influencing factor.

[0113] Understandably, both the first and second impact factors can be used as preset parameters for various applications.

[0114] S3043. Simulate the energy consumption level of the AOI machine under the resource allocation scheme. If the energy consumption level exceeds the preset energy-saving standard, adjust the resource allocation scheme. The preset energy-saving standard is determined based on the complexity of the task.

[0115] This process aims to identify whether the energy consumption of the AOI machine during operation based on the resource configuration scheme meets expectations, providing a data foundation for subsequent optimization and ensuring that energy consumption is controlled within a reasonable range. Furthermore, the preset energy-saving standard is determined based on the task complexity extracted from the user's current task request. Different task complexities can correspond to different preset energy-saving standards, enabling more energy-efficient AOI machine operation control while fulfilling the user's task requests.

[0116] In this embodiment, the resource allocation scheme is adjusted based on each influencing factor (i.e., the degree of influence of the first influencing factor and the second influencing factor). First, the degree of influence of each first influencing factor and the degree of influence of each second influencing factor are determined. The first influencing factors and the second influencing factors are prioritized according to their degree of influence, and the parameters in the resource allocation scheme are adjusted according to their priority.

[0117] If a certain first impact factor has the highest priority, then the parameter corresponding to the first impact factor will be adjusted first. That is, there is a mapping relationship between priority, adjustment order and adjustment magnitude.

[0118] The system provided by the embodiments of the present invention will be described below. The system described below can be referred to in correspondence with the method described above.

[0119] Please see Figure 4 , Figure 4 A schematic diagram of the energy-saving control system of an automatic optical inspection machine according to an embodiment of the present invention is shown. The system may include:

[0120] The task parsing module 10 is used to obtain the user's task request and determine the task complexity of each AOI machine included in the task request according to the preset task classification rules.

[0121] User-sent task requests can be presented in various forms such as text, forms, images, and structured data. After obtaining the task request, the various forms of task requests are parsed to extract features describing the complexity of the production task, i.e., complexity features are extracted. For example, pre-trained form segmentation models, text extraction models, and semantic analysis models are used for the above processing.

[0122] There are no restrictions on the specific form of complexity feature extraction, as long as the electronic device can acquire the complexity feature.

[0123] The task request issued to the AOI machine contains multiple task description details, such as start time, equipment number, operator number, and task content. These descriptions directly affect the assessment of task complexity. In this embodiment, these task descriptions are analyzed to extract features describing the complexity of the production task, such as the object to be inspected, defect type, environmental conditions (e.g., temperature), and required inspection accuracy. It should be noted that a single task request may contain production tasks from multiple AOI machines; therefore, a mapping relationship between the equipment used and the corresponding complexity features is established during extraction.

[0124] Determining the appropriate task complexity for each AOI machine can provide a reference for the initial configuration of subsequent operating parameters. Different task complexities correspond to different initial configuration strategies. The initial configuration operating parameters need to be able to adapt to the task complexity to ensure that the AOI machine can successfully complete the user's task request and then manage the AOI according to the task request. At the same time, different task complexities have different performance requirements for the AOI machine. By quantifying the task complexity through preset influencing items and influencing weights in the preset task classification rules, the task request can be accurately identified, laying the foundation for the adjustment of subsequent operating parameters.

[0125] The initial configuration module 20 is used to perform initial configuration of various operating parameters of the AOI machine according to the complexity of the task.

[0126] Initial parameter configuration based on task complexity ensures that the initial equipment configuration strategy closely aligns with production needs. For high-complexity tasks, an aggressive configuration strategy can be chosen to meet production demands, while a more conservative strategy can be selected for lower-complexity tasks to reduce resource consumption and extend equipment lifespan. This flexible configuration approach provides diverse options for equipment operation and effectively improves operational stability, especially crucial in highly complex task scenarios where proper configuration is paramount.

[0127] The energy-saving control module 30 is used to determine the minimum operating power required to meet the task request based on various operating parameters, acquire various equipment status parameters of the AOI machine under the initial configuration, use the minimum operating power as the adjustment benchmark, and adjust the operating parameters according to the equipment status parameters. These equipment status parameters include equipment temperature, load occupancy rate, and runtime, and directly reflect the actual status of the AOI machine.

[0128] For example, the temperature of an AOI machine reflects its operating status; excessively high temperatures may lead to performance degradation. Load utilization indicates resource usage; high load may increase the risk of failure. Running time is related to the degree of equipment fatigue.

[0129] In this embodiment, the minimum operating power is the minimum value of the AOI machine's operating power when the task request is met. Using the minimum operating power as the adjustment benchmark can avoid focusing solely on energy saving while neglecting production needs during the adjustment process. Furthermore, determining the minimum operating power also allows for the determination of a power adjustment range. This range not only characterizes the adjustment magnitude of the AOI machine's operating power in a single adjustment but also ensures the stability and reliability of the operating parameter adjustments, guaranteeing that the AOI machine operates in a stable state during adjustment.

[0130] In this embodiment, the rationality of the power adjustment range can be further analyzed for the adjustment of operating parameters. If the AOI machine needs to frequently adjust its operating power according to the power adjustment range, it may mean that the power adjustment range is set too narrowly. In order to optimize the adjustment time and cost of operating parameters, the range of the power adjustment range can be appropriately widened in subsequent adjustment processes, thereby reducing unnecessary adjustments and improving operational stability.

[0131] When acquiring various equipment status parameters of the AOI machine under initial configuration, data can be collected through various sensors, and the data transmitted by the sensors can be uniformly converted into a standard format. For example, temperature data is expressed in degrees Celsius, and load occupancy rate is expressed as a percentage. This forms a standardized set of equipment status parameters, which facilitates subsequent comparison and analysis and ensures data consistency.

[0132] It should be noted that the energy-saving control module 30 is configured with a dynamic adjustment mechanism, that is, adjusting the operating parameters and generating new operating parameters, running the corresponding AOI machine with the new operating parameters and continuously acquiring various equipment status parameters, or using the minimum operating power as the adjustment benchmark and adjusting the operating parameters according to the equipment status parameters. For the updated operating parameters, in this embodiment, it will determine whether dynamic adjustment is needed. Through real-time monitoring and feedback, it is ensured that the power adjustment can be truly implemented in the equipment operation, ensuring that the equipment can remain stable even in complex operating environments. This not only improves the response speed of adjustment, but also reduces equipment wear and extends service life through precise adjustment.

[0133] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An energy-saving control method for an automatic optical inspection machine, characterized in that: The method includes: The task request of the user is obtained, and the task complexity of each automatic optical inspection machine in the task request is determined according to the preset task classification rules. The preset task classification rules include several preset influence items and the influence weight of each preset influence item. Each preset influence item has a maximum preset threshold and a minimum preset threshold. The minimum and maximum preset thresholds define the preset threshold range of the preset influence item. Based on the complexity of the task, perform the initial configuration of various operating parameters of the automatic optical inspection machine; Determine the minimum operating power required to meet the task request based on various operating parameters, obtain the various equipment status parameters of the automatic optical inspection machine under the initial configuration, use the minimum operating power as the adjustment benchmark, and adjust the operating parameters according to the equipment status parameters; The process of obtaining user task requests, and determining the task complexity of each automated optical inspection machine included in the task request according to preset task classification rules, specifically includes: Obtain the user's task request and extract the task description information from the task request; The equipment information and complexity features are filtered out from the task description information, and a mapping relationship is established between each piece of equipment information and its corresponding complexity feature; each piece of equipment information corresponds to an automatic optical inspection machine. Based on the preset task classification rules, the complexity characteristics of each piece of equipment information are matched with the preset influencing items to obtain the task complexity of the automatic optical inspection machine corresponding to each piece of equipment information. Specifically, the step of matching the complexity features of each piece of equipment information with preset influence items according to preset task classification rules to obtain the task complexity of the automatic optical inspection machine corresponding to each piece of equipment information includes: According to the preset task classification rules, each complexity feature is matched with the corresponding preset influence item; based on the correlation between the feature value of the complexity feature and the preset threshold range of the preset influence item, the feature matching score of each complexity feature is determined. The influence score of each complexity feature is obtained based on the feature matching score of each complexity feature and the influence weight of the preset influence item. By aggregating the influence scores of all complexity features for each piece of equipment used, the task complexity of the corresponding automated optical inspection machine can be obtained.

2. The energy-saving control method for the automatic optical inspection machine as described in claim 1, characterized in that: The process of determining the minimum operating power required to meet the task request based on various operating parameters, acquiring various equipment status parameters of the automatic optical inspection machine under the initial configuration, using the minimum operating power as an adjustment benchmark, and adjusting the operating parameters according to the equipment status parameters specifically includes: The minimum operating power, power adjustment range, and optimal operating power are determined based on various operating parameters; the value of the optimal operating power exceeds the value of the minimum operating power. Acquire the various equipment status parameters of the automated optical inspection machine under its initial configuration; The device status parameters are compared with the corresponding preset device parameters to obtain the comparison results; Based on the comparison results, determine whether the operating parameters need to be adjusted. If it is determined that the operating parameters need to be adjusted, use the lowest operating power as the adjustment benchmark and the power adjustment range as the step size to iteratively adjust the operating parameters until it is determined that the operating parameters do not need to be adjusted based on the comparison results.

3. The energy-saving control method for the automatic optical inspection machine as described in claim 1, characterized in that: The method further includes: The system acquires control signal frequency and power fluctuation data of the automated optical inspection machine under adjusted operating parameters, and generates a resource configuration scheme for the automated optical inspection machine based on the control signal frequency and power fluctuation data.

4. The energy-saving control method for the automatic optical inspection machine as described in claim 3, characterized in that: The process of acquiring control signal frequency and power fluctuation data of the automated optical inspection machine under adjusted operating parameters, and generating a resource allocation scheme for the automated optical inspection machine based on the control signal frequency and power fluctuation data, specifically includes: Acquire control signal frequency and power fluctuation data of the automatic optical inspection machine under adjusted operating parameters; Determine the first influencing factor of the control signal frequency and the second influencing factor of the power fluctuation data; The energy consumption level of the simulated automatic optical inspection machine under the resource allocation scheme is measured. If the energy consumption level exceeds the preset energy-saving standard, the resource allocation scheme is adjusted. The preset energy-saving standard is determined based on the complexity of the task.

5. The energy-saving control method for the automatic optical inspection machine as described in claim 4, characterized in that: The adjustment of the resource allocation scheme is based on the degree of influence of the first influencing factor and the second influencing factor. The first influencing factor and the second influencing factor are prioritized according to the degree of influence. The priority is mapped to the adjustment order and the adjustment range.

6. The energy-saving control method for the automatic optical inspection machine as described in claim 1, characterized in that: The initial configuration of various operating parameters of the automatic optical inspection machine, based on the complexity of the task, specifically includes: Features with complexity whose feature matching scores exceed a preset score are marked as priority features; Preset control strategies are retrieved from the preset strategy library based on priority configuration features and task complexity; the preset strategy library stores several preset control strategies, each with corresponding preset parameters. Based on the preset parameters in the preset control strategy, the initial configuration of various operating parameters of the automatic optical inspection machine is performed.

7. The energy-saving control method for the automatic optical inspection machine as described in claim 6, characterized in that: The initial configuration of various operating parameters of the automatic optical inspection machine according to the complexity of the task also includes: If the number of priority configuration features exceeds the preset number, the retrieved preset control strategy is upgraded to obtain an updated preset control strategy.

8. An energy-saving control system for an automatic optical inspection machine, characterized in that: The system is used to implement the method as described in any one of claims 1-7, comprising: The task parsing module is used to obtain the user's task request and determine the task complexity of each automatic optical inspection machine included in the task request according to the preset task classification rules. The preset task classification rules include several preset influence items and the influence weight of each preset influence item. Each preset influence item has a maximum preset threshold and a minimum preset threshold. The minimum and maximum preset thresholds define the preset threshold range of the preset influence item. The initial configuration module is used to configure the various operating parameters of the automatic optical inspection machine according to the complexity of the task. The energy-saving control module is used to determine the minimum operating power required to meet the task request based on various operating parameters, acquire various equipment status parameters of the automatic optical inspection machine under the initial configuration, use the minimum operating power as the adjustment benchmark, and adjust the operating parameters according to the equipment status parameters.

Images