Intelligent early warning method in milling and drilling process and related equipment

Abstract

The invention provides an intelligent early warning method in a milling and drilling process and related equipment, and relates to the technical field of intelligent early warning. The method comprises the following steps: acquiring a plurality of target habit operations of an operator, splicing the target habit operations into sequential habit operation combinations at least containing two operations in an out-of-order manner, calculating a hazard score of each combination, and determining the combination with the score exceeding a preset threshold value as a hazard habit operation combination; acquiring a habit operation sequence of an operator and a first habit operation in the habit operation sequence, extracting a plurality of habit combinations of which the first action is the first habit operation in the harmful habit operation combination, and judging whether the next habit operation has an accident risk or not according to the habit operation sequence and the habit combinations, if yes, early warning is given to the display end, and the milling drill is controlled to delay working. According to the method, the habitual dangerous operation combination of an operator can be recognized in real time, the accident risk in the milling and drilling process is pre-judged, and the safety accident rate is reduced through early warning and equipment control.

Description

Technical Field

[0001] The present application relates to the field of intelligent early warning technology, and in particular to an intelligent early warning method and related equipment in a milling and drilling process. Background Art

[0002] In the field of mechanical manufacturing, milling and drilling is an important process. Some processing steps in the milling and drilling process are full of dangers, and the operator's safety awareness is very demanding.

[0003] At present, some novice operators in the milling and drilling process are taught by teachers who teach them the precautions during the operation and tell them the precautions during the milling and drilling process to prevent novice operators from doing certain actions without knowing it and causing serious consequences.

[0004] However, since it's impossible for a trainer to always be by a novice operator's side to provide supervision and guidance, novice operators often develop their own operating habits during actual work. These habits may seem unrelated to safety, such as habitually adjusting work clothes, wiping the surface of equipment, or checking their phones. However, when these habitual actions occur in a specific combination and sequence, a dangerous cumulative effect can occur. For example, if an operator habitually adjusts their work clothes while the equipment is running, and then habitually wipes the surface of the equipment with their hands, this combination may cause the operator's clothing to be caught in the equipment, resulting in a serious accident. Therefore, existing technologies have difficulty predicting production risks caused by operators' personal habits, etc., which can easily lead to major operational accidents. Summary of the Invention

[0005] The present application provides an intelligent early warning method and related equipment during the milling and drilling process, which is used to identify the operator's habitual dangerous operation combinations in real time, predict the accident risks during the milling and drilling process, and reduce the occurrence rate of safety accidents through early warning and equipment control.

[0006] In the first aspect, the present application provides an intelligent early warning method during the milling and drilling process, the method comprising: after obtaining multiple target habit operations of the operator during the milling and drilling process, piecing together the multiple target habit operations in random order to obtain multiple habit operation combinations with operation sequences after piecing together, the habit operation combination including at least two habit operations; obtaining the hazard scores of different habit operation combinations; when the hazard score is greater than a preset score threshold, determining the corresponding habit operation combination as a hazardous habit operation combination; obtaining the operator's habit operation sequence and the first habit operation in the habit operation sequence; extracting multiple habit combinations in which the first action in each of the hazardous habit operation combinations is the first habit operation; judging whether the operator's next habit operation will have an accident risk based on the habit operation sequence and the multiple habit combinations; if so, sending a warning message to the display end, and controlling the milling and drilling to suspend work.

[0007] By employing this technical solution, the operator's multiple target habitual actions are first captured and randomly assembled into combinations. Hazard scores are then calculated to screen for dangerous combinations. The system then combines the operator's habitual action sequence with the dangerous combination matching the first action to determine whether the next action is risky. This enables systematic identification of dangerous habitual combinations in milling and drilling operations. This analysis, based on operation sequences and historical dangerous combinations, can proactively predict potential accident risks caused by the operator's disordered habitual action combinations, shifting from passive emergency response to active prevention, improving the safety of the milling and drilling process, and reducing safety incidents caused by human operating habits.

[0008] In combination with some embodiments of the first aspect, in some embodiments, the step of obtaining multiple target habitual operations of the operator during the milling and drilling process specifically includes: obtaining the operating actions of the operator within a set distance area from the processing equipment during the processing; if the action frequency of the operating action is greater than the set frequency threshold, and the matching value with the standard operating action is less than the set matching value, the corresponding operating action is determined as the target habitual operation, and the standard operating action is the operating action of the processing equipment during the processing.

[0009] By employing this technical solution, we first limit the spatial scope of operational actions (within a set distance from the device), and then, through dual screening using action frequency and standard action matching values, we precisely locate frequently occurring, non-compliant, habitual actions. Spatial scope limitation ensures focus on the effective operating area, frequency thresholds eliminate sporadic actions, and matching values ​​filter out compliant actions. This triple mechanism ensures the accuracy and risk-based nature of targeted habitual actions, providing a reliable data foundation for subsequent risk combination analysis and preventing invalid data from interfering with risk assessment.

[0010] In combination with some embodiments of the first aspect, in some embodiments, before the step of obtaining the operator's habitual operation sequence, it also includes: when the operator performs multiple equipment production tasks, classifying the current habitual operation into equipment production tasks; determining the habitual operation sequence according to the habitual operations and action sequence corresponding to the same type of equipment production tasks.

[0011] By employing this technical solution, customary operations in multi-task scenarios are categorized by equipment production tasks. These operations are then bound to the target production area and equipment, ensuring a strong correlation between customary operation sequences and actual task scenarios. This classification mechanism prevents confusion between operation sequences across different tasks, making subsequent risk assessments more targeted. For example, the regularity of operation sequences within the same equipment task makes it easier to identify unusual combinations, improving the accuracy of risk prediction and task adaptability. This is particularly suitable for multi-task safety management on complex production lines.

[0012] In combination with some embodiments of the first aspect, in some embodiments, the step of classifying the current habitual operation into an equipment production task includes: determining the target production area and target production equipment corresponding to the equipment production task currently being performed by the operator; if the operator is in the target production area and is performing the habitual operation on the target production equipment, the habitual operation is bound to the target production equipment task.

[0013] By employing this technical solution, customary operations are bound to tasks based on dual verification of physical location (target production area) and equipment operation, strengthening the contextual attributes of the operation sequence. Physical location confirms the operator's actual work area, while equipment operation verifies the task type. This dual binding ensures the accuracy of customary operation classification, avoiding risk model matching errors caused by misjudgment of task type. This provides a reliable basis for the subsequent construction of a dedicated hazard combination library by task type, improving the task-specificity and reliability of the early warning system.

[0014] In combination with some embodiments of the first aspect, in some embodiments, the acquisition of the operator's habitual operation sequence specifically includes: acquiring the time point information corresponding to each habitual operation in the operator's habitual operation sequence; based on the time point information, calculating the time difference between each habitual operation; if the time difference is greater than the set time difference threshold, using the next habitual operation as the starting action of the acquisition of the operator's habitual operation sequence.

[0015] By employing this technical solution, customary operations are bound to tasks based on dual verification of physical location (target production area) and equipment operation, strengthening the contextual attributes of the operation sequence. Physical location confirms the operator's actual work area, while equipment operation verifies the task type. This dual binding ensures the accuracy of customary operation classification, avoiding risk model matching errors caused by misjudgment of task type. This provides a reliable basis for the subsequent construction of a dedicated hazard combination library by task type, improving the task-specificity and reliability of the early warning system.

[0016] In conjunction with some embodiments of the first aspect, in some embodiments, before the step of extracting multiple habit combinations in which the first action in each of the harmful habit operation combinations is the first habit operation, the method further includes: Determine the operator's identity information based on the camera; The hazardous habitual operation combination corresponding to the operator is determined according to the identity information.

[0017] By employing this technical solution, cameras first identify operators and then match them with their unique risk-prone operating habits, achieving personalized hazard warnings. Identity recognition distinguishes between different operator habits (e.g., the operating habits of novice and experienced operators present different risks). A dedicated risk combination library stores individual historical risk data, enabling the warning system to dynamically adjust risk assessment criteria based on the operator's skill level and habits. This improves warning accuracy and individual adaptability, reducing the false alarm rate of one-size-fits-all warnings.

[0018] In combination with some embodiments of the first aspect, in some embodiments, the determination of whether the operator's next habitual operation will have an accident risk is made based on the habitual operation sequence and the multiple habitual combinations, including: obtaining a first number of the habitual operation sequences; obtaining a target operation combination in which the number of operation actions in each of the habitual combinations is a second number, where the second number is one plus the first number; comparing the habitual operation sequence with the first number of habitual operation sequences before the target operation combination; if the comparison results are consistent, determining that the operator's next habitual action is about to have an accident risk.

[0019] By adopting this technical solution, a target action combination of "first quantity + 1" is set, and the current habitual action sequence is compared with the preceding action of the dangerous combination, enabling predictive risk assessment of the next action. The quantity difference ensures that the comparison focuses on the "imminent" subsequent action, while consistency verification of the preceding action identifies the triggering conditions of the dangerous combination. This "sequence matching + incremental prediction" mechanism provides timely warnings when the operator reaches the critical point of the dangerous combination, blocking the last link in the accident chain, minimizing the probability of risk occurrence, and improving the timeliness of warnings and the effectiveness of intervention.

[0020] In a second aspect, the present application provides an intelligent early warning system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the intelligent early warning system to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, the present application provides a computer-readable storage medium comprising instructions, which, when executed on an intelligent early warning system, enables the intelligent early warning system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, the present application provides a computer program product, which, when running on an intelligent early warning system, enables the intelligent early warning system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0023] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. Due to the technical means of piecing together the operator's multiple target habitual operations in random order to obtain a habitual operation combination, calculating the hazard score of each combination to screen the dangerous combination, and then combining the operator's habitual operation sequence and the dangerous combination matching the first action to judge the next operation risk, the problem in the existing technology that it is difficult to predict in advance the potential accident risks caused by the disordered combination of habitual actions in milling and drilling operations has been effectively solved. The systemic identification of dangerous habit combinations of milling and drilling operations has been realized, and the passive emergency response has been changed to active prevention, thereby improving the safety of the milling and drilling process and reducing the technical effect of safety accidents caused by human operating habits.

[0024] 2. Since the technical means of classifying the current habitual operations according to the equipment production tasks when the operator performs multiple equipment production tasks and determining the habitual operation sequence according to the habitual operations and action sequences corresponding to the same type of tasks is adopted, the problems of confusion in the operation sequences of different tasks in multi-task scenarios and lack of targeted risk judgment in the existing technology are effectively solved, thereby achieving a strong correlation between the habitual operation sequence and the actual task scenario, improving the accuracy of risk prediction and task adaptability, and being suitable for the technical effect of multi-task safety management of complex production lines.

[0025] 3. By adopting the technical means of obtaining the time point information of each habitual operation in the habitual operation sequence, calculating the time difference between operations, and determining the start action of the sequence based on the time difference threshold, the problem of misjudgment of sequence breaks and operation sequences not conforming to actual logic caused by long operation intervals in the existing technology is effectively solved. This further achieves the technical effect of making the habitual operation sequence more consistent with the actual operation process and improving the accuracy of risk judgment timing and logical rationality. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a system framework diagram of the intelligent early warning method in the milling and drilling process of the embodiment of the present application. Figure 2 This is a flow chart of an intelligent early warning method in the milling and drilling process according to an embodiment of the present application; Figure 3 This is another flow chart of the intelligent early warning method in the milling and drilling process according to an embodiment of the present application; Figure 4 It is a schematic diagram of the structure of a physical device of the intelligent early warning system in the embodiment of the present application. DETAILED DESCRIPTION

[0027] The terms used in the following examples of the present application are for the purpose of describing specific embodiments only and are not intended to limit the present application. As used in the specification and appended claims of the present application, the singular expressions "a," "an," "said," "above," "the," and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to and encompasses any or all possible combinations of one or more of the listed items.

[0028] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0029] For ease of understanding, the following describes the system to which the method provided in this embodiment is applied. Figure 1 , which is a system framework diagram of the intelligent early warning method in the milling and drilling process in the embodiment of the present application.

[0030] Figure 1 In this application, the intelligent early warning system refers to a software system deployed on milling and drilling equipment or a production management platform, and a camera is set at a preset position corresponding to the operator's operating area, which is used to collect pictures of the operator's operating actions during the milling and drilling process, and transmit them to the intelligent early warning system; the intelligent early warning system receives the operating action pictures from the camera, analyzes and judges the operator's operations, and if it is determined that there is an accident risk, it can send an early warning message to the display end, and control the milling and drilling equipment to enter a suspended operation state, so as to intervene in the milling and drilling process and ensure operational safety; the operator performs processing operations at the milling and drilling equipment, and his operating behavior is the object of monitoring and analysis by the intelligent early warning system; the milling and drilling equipment is the execution equipment of the processing operation, which is controlled by the intelligent early warning system and suspends operation when there is a risk.

[0031] For ease of understanding, the following describes the methods provided by this implementation. Figure 2 , which is a flow chart of the intelligent early warning method during the milling and drilling process in an embodiment of the present application.

[0032] S201, after acquiring multiple target habitual operations of the operator during the milling and drilling process, shuffling the multiple target habitual operations together in random order to obtain multiple habitual operation combinations with operation sequences after shuffling, the habitual operation combinations including at least two habitual operations; Among them, the milling and drilling process refers to the full-process mechanical processing operation covering workpiece clamping, parameter adjustment, cutting processing, tool inspection and other links; the operator refers to the person who performs the milling and drilling tasks, and his operating behavior includes personalized habitual actions (such as one-handed clamping, manual chip cleaning) and equipment control actions (such as starting the spindle, adjusting the feed rate); target habitual operations refer to repetitive actions generated by the operator based on personal habits rather than work requirements, and are not limited to equipment operations, such as not using a fixture when adjusting the workpiece position, and directly cleaning chips by hand after processing; disordered patchwork refers to the process in which the system rearranges and combines multiple target habitual operations of the same operator in all possible orders to generate a new action sequence; habitual operation combination refers to an ordered sequence composed of at least two target habitual operations, such as [adjusting the workpiece position → grabbing the workpiece by hand], [cleaning chips → quickly starting the spindle].

[0033] Specifically, this step is performed after acquiring multiple target habitual operations from the operator. In practical applications, the system first collects data on the operator's operational behavior during the milling and drilling process using sensors, cameras, and other devices, and identifies regular target habitual operations. After acquiring these target habitual operations, the system randomly combines and reorders them to form multiple new combinations. This process is similar to reshuffling a deck of playing cards: the previously ordered operations are shuffled and reassembled, resulting in a variety of different operation sequence combinations. Each combination must contain at least two habitual operations, as a single operation may not be sufficient to reflect potential hazards. This random combination is intended to simulate a variety of possible operation combinations, including improper operation sequences that could potentially lead to safety hazards. In this way, the system can proactively identify potentially dangerous operation combinations, providing basic data support for subsequent risk warnings. During the combination process, the system retains the specific attributes of each operation and records the order of operations to facilitate subsequent hazard analysis.

[0034] In some embodiments, the step of acquiring multiple target habitual operations of the operator during the milling and drilling process can be specifically determined as follows: first, the operating actions of a single operator within the set distance area from the processing equipment during the processing are acquired. If the action frequency of the operating action is greater than the set frequency threshold, and the matching value with the standard operating action is less than the set matching value, then the corresponding operating action is determined as the target habitual operation, and the standard operating action is the operating action of the processing equipment during the processing. Among them, the distance setting area refers to the pre-defined effective operating range between the operator and the equipment. The operating action represents all behavioral actions of the operator during the work process, including work actions and personal habitual actions. The action frequency refers to the frequency of repeated occurrence of a specific action. The standard operating action refers to the necessary work actions specified in the equipment operating procedures.

[0035] Specifically, this step aims to filter out those actions that stem from personal habits rather than work requirements from all the operator's movements. In actual production, in addition to performing necessary work actions, operators often make additional movements due to personal habits, especially when they are new to the job. Although these habitual movements are not related to the actual work, they may pose safety risks in certain situations.

[0036] The system first needs to determine its monitoring range, which typically encompasses the operator's surrounding space. Within this range, the system records all operator actions. These actions can be divided into two categories: standard operating procedures directly related to the job, such as adjusting parameters and changing workpieces; and habitual, individual operator actions unrelated to completing the task.

[0037] To identify habitual actions, the system adopts a "double screening" strategy: first, it looks at the frequency of the action. If an action is frequently repeated, it may be a habitual action. For example, some operators may be in the habit of tapping their fingers on the workbench every few minutes, or frequently fiddling with tools. These high-frequency actions are then compared with standard operating actions. If an action occurs frequently but does not match any standard work action (the matching value is low), then this action is likely a personal habitual action. For example, the standard operating action library does not include actions such as "touching the nose", so if this action occurs frequently, it will be identified as a habitual action. This can accurately distinguish between the operator's personal habitual actions and necessary work actions, effectively solving the problem of the existing technology that it is difficult to identify and distinguish personal habitual actions, resulting in warning blind spots or misjudgments, and thus realizes the accurate identification and targeted warning of the operator's personal habitual actions that truly pose potential risks.

[0038] S202. Obtaining harmfulness scores for different combinations of habitual operations; The "hazard score" is a quantitative assessment of the potential safety risk posed by a combination of customary operations. "Different customary operation combinations" refers to a combination of multiple different operation sequences formed by randomly combining them.

[0039] First, the system establishes assessment benchmarks based on two dimensions: accident frequency and severity. Regarding frequency, the system categorizes the frequency of accidents in historical data into multiple levels, such as high frequency (multiple times per month), medium frequency (multiple times per year), and low frequency (once every few years), creating an accident frequency template. Regarding severity, the system categorizes the severity of accidents into multiple levels, such as major, moderate, and minor, based on factors such as the resulting injuries, equipment damage, and production disruptions. This creates a severity template. When evaluating a new habitual operation combination, the system searches the historical database for cases similar to that combination and analyzes their frequency and severity. By calculating the similarity between the new operation combination and historical cases, the system predicts the potential accident risk associated with that combination. This similarity calculation takes into account multiple characteristics, such as the order of operations, time interval, and operating environment. Finally, the system uses the similarity calculation results, combined with the frequency and severity templates, to determine a final criticality score through a weighted calculation.

[0040] S203: When the harmfulness score is greater than a preset score threshold, the corresponding habitual operation combination is determined to be a harmful habitual operation combination; The Hazard Score represents a quantitative assessment of the potential risk posed by a specific habitual operation combination. The Preset Score Threshold is a system-defined safety threshold used to determine whether a habitual operation combination is potentially dangerous.

[0041] The habitual operation combination corresponding to the harmfulness score being greater than the preset score threshold is determined as the harmful habitual operation combination.

[0042] S204, obtaining the operator's habitual operation sequence and the first habitual operation in the habitual operation sequence; The habitual operation sequence refers to an ordered set of habitual operation actions performed by the operator in chronological order within a specific time period. The first habitual operation refers to the operation action that is performed first in the habitual operation sequence within the current observation period.

[0043] Specifically, this step involves capturing the operator's current sequence of actions during real-time monitoring. The system continuously collects operator action data using monitoring equipment such as cameras and sensors deployed in the work area. This data includes changes in the operator's position, body movements, and interactions with equipment. The system first preprocesses the collected raw data, including noise removal, data alignment, and action segmentation. Then, using an action recognition algorithm, it converts the processed data into specific action actions. These actions are timestamped to record the exact moment they occurred.

[0044] The system determines which actions belong to the same continuous sequence based on the time intervals between them. If the time interval between two actions exceeds a preset threshold (e.g., 30 minutes), they are considered two different sequences. For each identified sequence, the system extracts the first action as the first habitual action. This first habitual action is particularly important because it often marks the starting point of a combination of actions and may trigger a subsequent series of dangerous actions.

[0045] In some embodiments, to ensure temporal continuity of habitual operation sequences, it is important to avoid incorrectly combining habitual operations that occur at long intervals into the same sequence. In actual production, operators' habitual actions may occur at different time periods. If time intervals are not considered, completely unrelated habitual actions may be incorrectly associated, leading to inaccurate risk warnings.

[0046] The system first timestamps each identified habitual operation, recording the precise moment it occurred. This time information includes the date and time, accurate to the second. For example, the action "adjust workpiece position" occurs at "2023-10-15 14:30:25." The system stores this time information along with the characteristic data of the habitual operation to form a complete operation record. The system then calculates the time difference between consecutive habitual operations by subtracting the timestamp of the previous operation from the timestamp of the next operation. For example, if operation A occurs at 10:00 AM and operation B occurs at 2:00 PM, the time difference between them is 4 hours. This calculation takes into account the possibility of crossing days to ensure the accuracy of the time difference. The system then compares the calculated time difference with a preset time difference threshold. The setting of this threshold should take into account production practices, for example, it might be 30 minutes or 1 hour. If the time difference between two consecutive operations exceeds this threshold, the system will determine that the continuity between the two operations is interrupted and they should not belong to the same operation sequence.

[0047] In this case, the system will reconstruct a new operation sequence, starting with the operation that has a significant time difference. The reason for this is that the operation after a long time interval is more likely to be the beginning of a new work cycle, rather than a continuation of the previous operation sequence. For example, if an operator performs a habitual action before leaving get off work and then performs another habitual action after returning to work the next day, these two actions should obviously not be considered part of the same operation sequence.

[0048] In some embodiments, to improve the efficiency of matching harmful habitual operations, the operator's identity is first identified, and then only the harmful habitual operation combinations that have occurred in the operator's history are matched. This is because each operator has a specific habitual action pattern, and some harmful habitual operation combinations may only occur in specific operators. For example: Operator A may have a hazardous habitual operation combination such as "adjusting the workpiece - touching the hair - touching the moving parts"; Operator B may have a hazardous habitual operation combination of "knocking the equipment - shaking hands - touching the control button"; Operator C might have a hazardous habitual action sequence like "wiping sweat, rubbing eyes, and then checking the work surface." If the system doesn't perform identity recognition and personalized matching, it would need to compare the currently observed habitual action sequence with all known hazardous habitual action sequences, resulting in a significant waste of unnecessary computing resources. This is because operator A's habitual actions will likely never exhibit the hazardous action sequence patterns of operators B or C.

[0049] After identifying the operator through camera recognition and comparing that facial information with an existing employee database, the system quickly locates that operator's unique and potentially hazardous habit combinations. This personalized combination database records all of the operator's historically hazardous habit sequences. This allows the system to focus only on the operator's potential hazardous combinations during subsequent matching, significantly reducing ineffective matching operations.

[0050] S205, extracting multiple habit combinations whose first action in each of the harmful habit operation combinations is the first habit operation; The first action refers to the operation that ranks first in each harmful habitual operation combination. The first habitual operation refers to the operation that is first executed in the operation sequence currently being monitored.

[0051] Specifically, after obtaining the operator's current first habitual operation, this step extracts the relevant dangerous sequences from the pre-identified library of dangerous habitual operation combinations. The system first accesses the dangerous habitual operation combination database, which stores all operation combinations that have been determined to be dangerous. Each dangerous habitual operation combination contains complete operation action sequence information, including the type, execution order, time characteristics, etc. of each action. The system traverses all dangerous habitual operation combinations and checks the first action of each combination. For each dangerous combination, the system extracts its first operation action and matches it with the currently monitored first habitual operation. The matching process not only compares the action type, but also considers the specific characteristics of the action, such as action amplitude, duration, execution location, etc. Only when the first action and the current first habitual operation meet the similarity requirements in all feature dimensions will the dangerous combination be extracted and determined as a habitual combination.

[0052] During the actual execution process, the system will set a matching tolerance range, because the same type of action may have slight differences when performed by different operators at different times. For example, if the first habitual operation currently monitored is "quickly adjust the workpiece position", the system will look for all hazardous combinations that start with actions related to "adjusting the workpiece position". These actions may include variants such as "quick adjustment", "freehand adjustment", and "forced adjustment". The system will also take into account the execution environment of the action, such as the current operating status of the equipment, the processing stage of the workpiece, etc., to ensure that the extracted hazardous combinations match the current operating scenario.

[0053] S206: judging whether the operator's next habitual operation will have an accident risk based on the habitual operation sequence and the multiple habitual combinations; Specifically, this step involves obtaining the operator's current habitual operation sequence and potentially dangerous operation combinations, and then predicting the risk of the next operation through sequence matching. The system first counts the number of actions included in the current habitual operation sequence, recording this as the first number. This number reflects the number of consecutive actions the operator has completed. For example, if the operator has performed the three actions of "adjusting the workpiece position → inspecting the machined surface → taking a closer look," the first number is 3.

[0054] The system then selects combinations from the previously extracted hazardous habit combinations that have exactly one more action than the first set. These combinations are called target action combinations. The purpose of selecting combinations with one more action than the current sequence is to predict the next hazardous action. For example, if the current sequence contains three actions, the system will focus on all hazardous combinations containing four actions, as the fourth action in these combinations is likely the next action the operator will perform.

[0055] The system performs a detailed comparison of the current custom operation sequence with the first N actions (N equals the first number) of each target operation combination. This comparison not only checks for the same action types but also verifies that the order of actions, time intervals between actions, and operational characteristics match. For example, if the current sequence is "adjust workpiece position → inspect workpiece surface → take a closer look," the system will search for all four-action combinations whose first three actions exactly match it.

[0056] If the first N actions of a target action combination exactly match the current sequence, the system will flag the N+1th action (i.e., the fourth action) as a potentially dangerous action. This is because historical data shows that after an operator performs the same preceding action as the hazardous combination, they are likely to continue with the next action in the combination out of inertia, which has been confirmed to pose a safety risk.

[0057] During the entire judgment process, the system also takes into account the current operating environment and equipment status. For example, if the current equipment is in a high-speed operation state, then certain actions that are safe when the equipment is stationary may become dangerous. The system will adjust the weight and threshold of risk judgment according to the real-time status to ensure the accuracy and timeliness of the early warning. Among them, the habitual operation sequence refers to a series of continuous operation actions currently being performed by the operator. The first number represents the number of operation actions contained in the current habitual operation sequence. The habitual combination refers to an operation sequence extracted from the hazardous operation combination library, in which the first action matches the current first habitual operation. The second number refers to the number of operation actions contained in the target operation combination, and its value is equal to the first number plus 1. The target operation combination represents a dangerous sequence with the second number of operation actions selected from the habitual combination. Comparison refers to the process of matching two operation sequences for similarity. Accident risk refers to a dangerous situation that may lead to a safety accident.

[0058] S207: If yes, send a warning message to the display terminal and control the milling and drilling equipment to suspend operation.

[0059] Warning information refers to the system's alerts to the operator when it detects a potential safety risk. Display devices, including display screens, warning lights, and audible and visual alarms, convey warning information to the operator. Milling and drilling suspension refers to the process of temporarily stopping or reducing operating parameters of the milling and drilling equipment through the control system.

[0060] Specifically, this step is a safety intervention measure taken after the system determines that the operator's next habitual operation poses an accident risk, in order to remind the operator not to perform the next habitual operation that may cause harm. When the risk judgment result is "yes", the system will immediately activate a dual protection mechanism: on the one hand, it will send warning information to the operator in accordance with the preset warning method through various means; on the other hand, it will directly intervene in the operating status of the equipment. The warning information is sent in a multi-level and multi-channel manner to ensure that the operator can perceive the danger prompts in a timely manner, including a prominent warning window popping up on the most eye-catching display screen in the operating area, showing a specific reminder to the operator not to perform the next habitual operation that may cause harm. At the same time, the sound and light alarm device is activated to attract the operator's attention through warning lights of different colors and alarm sounds of specific frequencies.

[0061] The following example illustrates the entire logical process: The system obtains the number of actions in the current operation sequence [adjust workpiece position → clean chips → check tool] and determines that the first number is 3. It then filters through a stored library of dangerous combinations to identify combinations with four actions. Combination A: [adjust workpiece position → clean chips → check tool → manually grasp the workpiece] and combination B: [adjust workpiece position → clean chips → check tool → quickly start spindle]. Combination C: [adjust fixture → change tool → measure dimensions → adjust speed], although also consisting of four actions, is excluded because its sequence is completely different from the current sequence.

[0062] The system then conducts a detailed comparison of the current sequence with the first three actions of Combinations A and B. The comparison results show that the first three actions of both Combinations A and B are identical to the current sequence: "Adjust workpiece position → Clear chips → Check tool." This means that, based on historical data analysis, after completing these three actions, the operator may have performed the fourth action in Combination A, "Grab the workpiece by hand," or the fourth action in Combination B, "Quickly start the spindle." Both actions are marked as highly dangerous by the system, as manually grasping the workpiece could lead to work-related accidents, and quickly starting the spindle could pose a safety hazard due to insufficient pre-process checks.

[0063] In this case, the system will determine that the operator's next habitual action is highly likely to result in an accident risk. This is because the current action sequence perfectly matches the preceding actions of two known hazardous combinations, and the subsequent actions of both combinations present clear safety hazards. This sequence-matching-based risk assessment method can identify potential risks before a dangerous action actually occurs, providing a basis for early warning and intervention decisions.

[0064] In the embodiment of the present application, due to the technical solution of piecing together the operator's multiple target habitual operations in random order to obtain a habitual operation combination, calculating the hazard score to screen the dangerous combination, obtaining the real-time operation sequence and extracting the matching dangerous combination, predicting the risk of the next operation through sequence comparison, and timely issuing early warning and control equipment, it is possible to predict potential risks based on the development trend of the operator's habitual operation sequence before the operator actually performs the dangerous action, and take active preventive measures, effectively solving the problem of relying solely on experience judgment and being unable to systematically identify and prevent habitual dangerous operations in the prior art, thereby realizing intelligent and predictive prevention and control of safety hazards caused by operating habits in the milling and drilling process, and significantly improving production safety.

[0065] In a multi-device production environment, task differentiation is performed to avoid misjudgments caused by cross-device action sequences. In modern production workshops, multiple processing machines often operate in parallel, and an operator may need to switch back and forth between several adjacent machines. In this case, if the specific machine task currently being performed by the operator cannot be accurately identified, operations belonging to different machines may be incorrectly combined, causing the early warning system to misjudge.

[0066] After combining the above content, the following is a more detailed description of the process of the method provided by this implementation. Figure 2 , which is another flow chart of the intelligent early warning method during the milling and drilling process in an embodiment of the present application.

[0067] S301, determining the target production area and target production equipment corresponding to the equipment production task currently being performed by the operator; The "equipment production task" represents the processing work performed by an operator on a specific piece of production equipment. The "target production area" refers to the operating range of a specific piece of production equipment, including the equipment itself and the space necessary for operational activities. The "target production equipment" represents the specific processing equipment currently being operated by the operator.

[0068] The system first needs to spatially divide the production workshop and define a dedicated target production area for each piece of equipment. This area not only includes the space occupied by the equipment itself, but also takes into account the range of movement required by the operator for daily operations. For example, for a milling machine, its target production area should include: the equipment body area, the workpiece loading and unloading area, the operation panel operation area, the tool storage area, etc. The scope of these areas needs to be determined based on the equipment characteristics, process requirements, and ergonomic principles. At the same time, the system will set up multiple monitoring points for each target production area, using various means such as monitoring equipment such as cameras to monitor the operator's location and behavior in real time. The system will integrate and process the monitoring data sent by the monitoring equipment to construct a real-time location map of the operator within the workshop.

[0069] As the operator moves around the workshop, the system continuously analyzes changes in their position. If the operator is detected entering a target production area and staying in that area for longer than a preset threshold (for example, 30 seconds), the system will preliminarily determine that the operator may be working on the equipment in that area. However, location information alone is not enough, and the system needs to further confirm whether the operator is actually performing the production task of the equipment. To this end, the system will analyze the operator's specific actions. For example, whether the operation panel of the equipment is touched, whether the workpiece is adjusted, whether the processing parameters are checked, etc. Only when these actions clearly point to the operation of a certain equipment will the system finally determine that this is the operator's current target production equipment.

[0070] S302: If the operator is in the target production area and is performing a custom operation on the target production equipment, the custom operation is bound to the target production equipment task; Binding refers to establishing an association between a customary operation and a specific device task.

[0071] Specifically, this step involves correctly assigning observed habitual actions to specific equipment tasks after determining the operator's location and target equipment. Modern factories often utilize a multi-equipment collaborative production model, and a single operator may need to switch between multiple pieces of equipment. To avoid incorrectly associating operations across different pieces of equipment, the system must accurately determine the specific equipment task scope for each habitual action.

[0072] Once the system determines that the operator is in the target production area and performing a custom operation on the target production equipment, it initiates the binding process. This process creates a task-associated tag for each custom operation. This tag contains several key pieces of information: equipment ID, task type, operation timestamp, equipment status parameters, and more. This binding mechanism not only records the correspondence between custom operations and equipment but also preserves the specific environmental information in which the operation occurred. This information is crucial for subsequent risk analysis, as the same operation may have different risk levels depending on the equipment's state. For example, adjusting a workpiece is safe when the equipment is shut down, but can be very dangerous when the equipment is running.

[0073] S303: Determine a customary operation sequence according to customary operations and action sequences corresponding to production tasks of the same type of equipment.

[0074] Specifically, after binding custom operations to device tasks, this step organizes custom operations belonging to the same device task category into an ordered sequence. This step ensures that when analyzing operational risks, the system focuses only on logically related operation sequences, avoiding the mistaken combination of operations from different devices or different types of tasks.

[0075] The system first categorizes equipment production tasks. This categorization is primarily based on equipment type. For example, all vertical milling machines can be grouped together because their operating modes and process flows are generally similar. Similarly, equipment performing similar processing tasks can be grouped together. For example, all equipment performing precision parts processing can be grouped together because they have similar precision and process requirements. After determining the task classification, the system retrieves all habitual operator actions related to that task type (in the target area and on the target production equipment), sorts them by time sequence, and then re-executes step S204. These records contain detailed information such as action type, occurrence time, duration, and operational characteristics. Through this analysis, the system organizes truly relevant habitual actions into meaningful sequences. Each sequence contains complete operation chain information, including sequence start and end time, included operation steps, specific characteristics of each step, and the time interval between operations. This sequence information is stored in the system's sequence library and serves as the basis for subsequent risk analysis.

[0076] In the embodiment of the present application, due to the technical solution of determining the location according to the target production area where the operator is located and the target production equipment being operated, binding the habitual operation to the specific equipment task, and determining the habitual operation sequence based on the operation sequence corresponding to the same type of equipment task, it is possible to accurately identify and distinguish the operator's operating behavior between different devices, ensure the consistency and task relevance of the habitual operation sequence, and effectively solve the problem in the prior art of easily incorrectly combining the operating actions of different devices to cause false warning triggering, thereby realizing accurate identification of operating behaviors and risk warnings in a multi-device environment on the production site.

[0077] The following describes the intelligent early warning system in the embodiment of the present invention from the perspective of hardware processing. Figure 4 , is a schematic diagram of the physical device structure of the intelligent early warning system in an embodiment of the present application.

[0078] It should be noted that Figure 4 The structure of the intelligent early warning system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0079] like Figure 4As shown, the intelligent early warning system includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes, such as the methods described in the above embodiments, based on programs stored in a read-only memory (ROM) 402 or programs loaded from a storage unit 408 into a random access memory (RAM) 403. RAM 403 also stores various programs and data required for system operation. CPU 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to bus 404.

[0080] The following components are connected to the I / O interface 405: an input section 406 including an audio input device, push button switches, and the like; an output section 407 including a liquid crystal display (LCD), an audio output device, indicator lights, and the like; a storage section 408 including a hard disk and the like; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. Removable media 411, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 410 as needed, so that computer programs read from the removable media can be installed in the storage section 408 as needed.

[0081] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for executing the methods illustrated in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 409 and / or installed from removable media 411. When executed by central processing unit (CPU) 401, the computer program performs the various functions defined in the present invention.

[0082] It should be noted that specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0083] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings.

[0084] Specifically, the intelligent early warning system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the intelligent early warning method in the milling and drilling process provided by the above embodiment is implemented.

[0085] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the intelligent early warning system described in the above embodiments, or may exist independently and not be incorporated into the intelligent early warning system. The storage medium carries one or more computer programs, which, when executed by a processor of the intelligent early warning system, enable the intelligent early warning system to implement the intelligent early warning method for the milling and drilling process provided in the above embodiments.

[0086] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0087] As used in the above embodiments, the term “when” may be interpreted to mean “if” or “after” or “in response to determining that” or “in response to detecting that”, depending on the context. Similarly, the phrases “upon determining that” or “if (stated condition or event) is detected” may be interpreted to mean “if determining that” or “in response to determining that” or “upon detecting (stated condition or event)” or “in response to detecting (stated condition or event)”, depending on the context.

[0088] Those skilled in the art will appreciate that all or part of the process steps in the above-described method embodiments can be implemented by a computer program instructing the relevant hardware. The program can be stored in a computer-readable storage medium, and when executed, the program can include the process steps in the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. An intelligent early warning method in the milling and drilling process, characterized in that: The method comprises: After acquiring multiple target habitual operations of the operator during the milling and drilling process, the multiple target habitual operations are randomly assembled to obtain multiple habitual operation combinations with operation sequences after assembly, wherein the habitual operation combinations include at least two habitual operations; Obtain harmfulness scores for different combinations of habitual operations; When the harmfulness score is greater than a preset score threshold, the corresponding habitual operation combination is determined to be a harmful habitual operation combination; Acquiring an operator's habitual operation sequence and a first habitual operation in the habitual operation sequence; extracting a plurality of habit combinations in which the first action of each of the harmful habit operation combinations is the first habit operation; determining, based on the habitual operation sequence and the plurality of habitual combinations, whether the operator's next habitual operation will have an accident risk; If so, an early warning message is sent to the display terminal, and the milling and drilling equipment is controlled to suspend work.

2. The method according to claim 1, characterized in that The step of obtaining multiple target habitual operations of the operator during the milling and drilling process specifically includes: Obtain the operator's operating actions during the processing within the set distance area from the processing equipment; If the operation frequency of the operation action is greater than the set frequency threshold, and the matching value with the standard operation action is less than the set matching value, the corresponding operation action is determined as the target habitual operation, and the standard operation action is the operation action of the processing process on the processing equipment.

3. The method according to claim 1, characterized in that Before the step of obtaining the operator's habitual operation sequence, the following steps are also included: When the operator performs multiple equipment production tasks, the equipment production tasks are classified according to the current habitual operation; Determine the customary operation sequence based on the customary operations and action sequences corresponding to production tasks of the same type of equipment.

4. The method according to claim 3, characterized in that The step of classifying equipment production tasks for the current customary operation includes: Determine the target production area and target production equipment corresponding to the equipment production task currently being performed by the operator; If the operator is in the target production area and is performing a customary operation on the target production equipment, the customary operation is bound to the target production equipment task.

5. The method according to claim 1, wherein The step of obtaining the operator's habitual operation sequence specifically includes: Acquiring time point information corresponding to each habitual operation in the habitual operation sequence of the operator; Calculating the time difference between each of the habitual operations based on the time point information; If the time difference is greater than a set time difference threshold, the next habitual operation is used as the starting action for obtaining the operator's habitual operation sequence.

6. The method according to claim 1, characterized in that Before the step of extracting a plurality of habit combinations in which the first action in each of the harmful habit operation combinations is the first habit operation, the method further includes: Determine the operator's identity information based on the camera; The hazardous habitual operation combination corresponding to the operator is determined according to the identity information.

7. The method according to claim 1, characterized in that The determining, based on the habitual operation sequence and the plurality of habitual combinations, whether the operator's next habitual operation will have an accident risk includes: obtaining a first quantity of the habitual operation sequence; Obtaining a target operation combination having a second number of operation actions in each of the habitual combinations, where the second number is the first number plus one; comparing the habitual operation sequence with the first number of habitual operation sequences preceding the target operation combination; If the comparison results are consistent, it is determined that the operator's next habitual action will result in an accident risk.

8. An intelligent early warning system, characterized in that: The intelligent early warning system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the intelligent early warning system to execute the method described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on the intelligent early warning system, the intelligent early warning system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on an intelligent early warning system, the intelligent early warning system is enabled to execute the method according to any one of claims 1 to 7.

Images