Workbench production line control method and system based on environment state analysis

Abstract

The application provides a workbench production line control method and system based on environment state analysis, comprising the following steps: S1: arranging multiple environment sensors at each workbench, collecting multiple environment elements through the environment sensors, and uniformly modeling the collected environment data to obtain an environment data model; S2: performing feature extraction on the environment data model to extract state feature parameters corresponding to each environment element; S3: performing fusion calculation on the multiple environment elements according to the state feature parameters to obtain a fusion risk parameter representing the risk level of the current work station; S4: calculating the evolution trend of the risk level with time according to the environment data model and the fusion risk parameter to obtain a risk evolution result in a prediction period; S5: determining a corresponding risk grade according to the risk evolution result; and S6: triggering a corresponding control strategy according to the risk grade to control the running state of the workbench equipment, so that the safety performance of the workbench production line can be provided.

Description

Technical Field

[0001] This invention belongs to the field of Internet of Things (IoT) production line management, and particularly relates to a workbench production line control method and system based on environmental condition analysis. Background Technology

[0002] In existing technologies, safety management of workbench production lines typically employs a combination of environmental parameter monitoring and threshold alarms. For example, temperature, humidity, dust concentration, or gas concentration sensors are used to monitor the production environment in real time, and an alarm is triggered or corresponding control measures are taken when a certain environmental parameter exceeds a preset safety threshold.

[0003] However, the aforementioned safety production management methods still have the following shortcomings: On the one hand, existing technologies often monitor and manage different environmental elements separately, lacking unified modeling and collaborative analysis of multiple environmental elements. Inconsistencies in data structures, sampling periods, and processing methods among various environmental elements make it difficult to comprehensively assess the overall environmental state at the system level, easily leading to fragmented safety risk assessments. On the other hand, existing technologies mostly rely on instantaneous values ​​or fixed thresholds of single environmental elements for judgment, ignoring the trend characteristics and fluctuations of environmental elements over time. When environmental parameters fluctuate drastically in a short period or multiple elements change simultaneously, existing solutions struggle to identify potential safety hazards in a timely and accurate manner, posing a risk of false alarms or missed alarms.

[0004] Furthermore, existing safety production management plans typically focus on detecting single anomalies, lacking analysis of the relationships between multiple environmental factors. When multiple environmental factors undergo coordinated changes within the same time period, their cumulative risks are often underestimated, failing to reflect the true level of safety risks.

[0005] Meanwhile, most existing technologies only assess the current environmental state and do not analyze the evolution of risks over time, making it difficult to make forward-looking predictions of safety risks. This results in safety management remaining largely at the post-event response stage and lacking proactive prevention and control capabilities. Summary of the Invention

[0006] The purpose of this application is to provide a workbench production line control method and system based on environmental condition analysis, so as to improve the safety performance of workbench production line management.

[0007] To achieve the above objectives, one aspect of this application provides a workbench production line control method based on environmental state analysis, comprising: S1: arranging multiple environmental sensors on each workbench to collect multiple environmental elements, and uniformly modeling the collected environmental data to obtain an environmental data model; S2: extracting features from the environmental data model to extract state feature parameters corresponding to each environmental element; S3: performing fusion calculation on multiple environmental elements based on the state feature parameters to obtain a fusion risk parameter characterizing the current workstation risk level; S4: calculating the evolution trend of the risk level over time based on the environmental data model and the fusion risk parameter to obtain the risk evolution result within the prediction period; S5: identifying abnormal environmental conditions based on the risk evolution result and determining the corresponding risk level; S6: triggering a corresponding control strategy based on the risk level to control the operating state of the workbench equipment.

[0008] Preferably, S1 includes: the multiple environmental elements include one or more of temperature, humidity, dust concentration, toxic or combustible gas concentration, noise intensity, illuminance, and airflow parameters; the environmental data model is represented in the form of a multi-dimensional vector, wherein different dimensions correspond to real-time data sequences of different environmental elements.

[0009] Preferably, the step of uniformly modeling the collected environmental data includes: synchronizing the collected environmental data and mapping the synchronized environmental data to a unified data structure to form an environmental data model that includes time dimension and environmental element dimension.

[0010] Preferably, S2 includes: the state feature parameters are calculated based on environmental data within a preset time window in the environmental data model, and the state feature parameters include one or more of the following: current state parameters, trend feature parameters, and fluctuation feature parameters.

[0011] Preferably, the fluctuation characteristic parameters are obtained by calculating the magnitude or dispersion of changes in environmental factors within the preset time window.

[0012] Preferably, before S3, the method further includes setting weights for different environmental factors, wherein the weights are preset according to the degree of impact of the environmental factors on safe production.

[0013] Preferably, S3 includes: the fusion risk parameter is obtained by weighting the state characteristic parameters of each environmental element with their corresponding weights.

[0014] Preferably, setting weights for different environmental elements includes: when at least two environmental elements meet preset association conditions within the same time period, it is determined that there is a coupling risk association between the environmental elements; when a coupling risk association is determined, the weight of the corresponding environmental element in the fusion calculation is amplified.

[0015] Preferably, the preset association conditions include: the change magnitude of the at least two environmental elements within the same time period exceeds the corresponding change threshold, and the change of the at least two environmental elements occurs within a preset time tolerance.

[0016] This application, in another aspect, provides a workbench production line control based on environmental state analysis. Using the aforementioned management method, it includes: an environmental data acquisition module configured to deploy multiple environmental sensors on each workbench to collect data on multiple environmental elements; a data modeling module configured to uniformly model the collected environmental data to form an environmental data model; a feature extraction module configured to extract features from the environmental data model to obtain state feature parameters corresponding to each environmental element; a risk fusion calculation module configured to perform fusion calculations on multiple environmental elements based on the state feature parameters to generate fused risk parameters characterizing the current workstation's risk level; a risk evolution analysis module configured to calculate the evolution trend of the risk level over time based on the environmental data model and the fused risk parameters, and obtain the risk evolution result within the predicted time period; an anomaly identification and risk classification module configured to identify environmental anomalies based on the risk evolution result and determine the corresponding risk level; and a control strategy execution module configured to trigger a corresponding control strategy based on the risk level to control the operating status of the workbench equipment.

[0017] The technical solution provided in this application can achieve the following beneficial effects: 1. This application synchronously processes and uniformly models multiple environmental element data. Under a unified data structure, it extracts current state characteristic parameters, trend characteristic parameters, and fluctuation characteristic parameters based on a preset time window, so that the assessment of environmental state no longer depends on the instantaneous value at a single moment. By introducing statistical and change characteristics within the time window, this application can effectively suppress misjudgments caused by instantaneous disturbances or occasional noise in environmental data and improve the credibility of environmental state identification.

[0018] 2. Before risk fusion calculation, this application sets basic weights for different environmental elements, and when multiple environmental elements are detected to meet preset association conditions at the same time, it determines that there is a coupled risk association and dynamically amplifies the weight of the corresponding environmental element. Through the above mechanism, this application can identify potential superimposed risks in advance when multiple environmental elements are abnormal at the same time but have not yet exceeded a single safety threshold, thereby avoiding the problem that multi-element collaborative anomalies are underestimated by traditional single-element analysis methods, and significantly improving the identification sensitivity in complex safety risk scenarios.

[0019] 3. This application not only generates fused risk parameters representing the current workstation risk level based on state characteristic parameters, but also further combines environmental data models to analyze the evolution trend of risk level over time, and obtain the risk evolution results within the prediction period. Through the analysis of risk evolution trend, this application can identify its continuous upward trend before the risk reaches the alarm threshold, thereby providing advance notice for safety intervention and transforming safety management from passive response to proactive prevention.

[0020] 4. This application classifies workstation risks based on the risk evolution results and triggers differentiated control strategies based on different risk levels to control the operating status of workbench equipment. Through the correspondence between risk levels and control strategies, this application can take lightweight intervention measures in the low-risk or controllable stage and take mandatory control measures in the high-risk stage, thereby ensuring production safety while reducing unnecessary downtime or excessive control and improving the overall efficiency of production line operation. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application 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 embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0022] Figure 1 This is a flowchart of a workbench production line control method based on environmental state analysis provided in an embodiment of this application; Figure 2 This is a flowchart of the environmental element data processing method provided in the embodiments of this application; Figure 3 This is a flowchart of the method for calculating the change range provided in the embodiments of this application; Figure 4 This is a flowchart illustrating the standard deviation calculation method provided in the embodiments of this application; Figure 5 This is a flowchart of the method for calculating fusion risk parameters provided in the embodiments of this application; Figure 6 This is a flowchart of the weight adjustment method provided in the embodiments of this application; Figure 7 This is a schematic diagram of a workbench production line control system based on environmental state analysis, provided in an embodiment of this application. Detailed Implementation

[0023] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0024] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0025] This embodiment provides a workbench production line control method based on environmental state analysis, which is applicable to production line scenarios with multiple workbenches and is used for real-time management and control of environmental safety risks in the production process.

[0026] The aforementioned workbench production line control method based on environmental condition analysis, such as... Figure 1 As shown, S1: Perform multi-environmental element collection and unified modeling. Specifically, in this embodiment, various environmental sensors are arranged at each workbench position on the production line. The environmental sensors include at least one or more of the following: temperature sensor, humidity sensor, gas concentration sensor, dust sensor, and noise sensor, which are used to collect data on various environmental elements that reflect the working environment status of the workbench.

[0027] Each environmental sensor connects to the data processing unit via IoT communication, uploading the collected environmental data in real time or periodically. To facilitate subsequent unified processing and analysis, raw environmental data from different sensors and environmental elements are uniformly modeled and processed. The multi-source environmental data is organized according to a preset data structure and time stamp to form an environmental data model. This environmental data model describes the state of multiple environmental elements corresponding to each workstation at the same time dimension.

[0028] S2: Perform feature extraction on the environmental data model. Specifically, after obtaining the environmental data model, perform feature extraction processing on the environmental data model to extract the state feature parameters corresponding to each environmental element.

[0029] In this embodiment, the state feature parameters are used to characterize the state characteristics of environmental elements at present or within a certain time range, including but not limited to the current numerical characteristics, trend characteristics, and fluctuation characteristics of environmental elements. Through feature extraction processing, the raw environmental data is transformed into state feature parameters that can reflect the laws of environmental state change, thereby reducing data redundancy and improving the effectiveness of subsequent risk analysis.

[0030] S3: Perform fusion calculation of multiple environmental elements. Specifically, after extracting the state feature parameters corresponding to each environmental element, perform fusion calculation of multiple environmental elements based on the state feature parameters.

[0031] In this embodiment, state characteristic parameters from different environmental elements are comprehensively analyzed according to preset fusion rules to obtain a fused risk parameter that can comprehensively characterize the current safety status of the workbench environment. This fused risk parameter reflects the overall risk level under the combined effect of multiple environmental elements, avoiding misjudgments caused by relying solely on a single environmental element.

[0032] S4: Calculate the risk evolution trend. Specifically, after obtaining the fused risk parameters, calculate the evolution trend of the risk level over time by combining the environmental data model.

[0033] In this embodiment, by analyzing the changes in fused risk parameters over a continuous time period, the trend of risk level changes is calculated, and based on this, the risk evolution over a future prediction period is extrapolated to obtain the risk evolution result for the prediction period. The risk evolution result reflects whether the risk exhibits a continuous upward, downward, or fluctuating trend, thus providing a time-dimensional basis for anomaly identification.

[0034] S5: Perform environmental anomaly identification and risk level determination. Specifically, after obtaining the risk evolution results, judge the current environmental status of the workbench based on the risk evolution results to identify whether there are any environmental anomalies.

[0035] When the risk evolution results indicate that the risk level exceeds the preset safety range, or shows an evolutionary trend that is detrimental to safe production, the corresponding workbench environment is determined to be abnormal, and the corresponding risk level is further determined based on the risk evolution results. The risk level is used to distinguish different degrees of safety risk in order to take differentiated management measures.

[0036] S6: Trigger a control strategy based on risk level. Specifically, after determining the risk level, trigger the corresponding control strategy according to the risk level to control the operating status of the workbench equipment.

[0037] In this embodiment, the control strategy may include measures such as adjusting the operating parameters of the workbench equipment, limiting the intensity of work, switching the equipment's operating status, or issuing safety warnings. By implementing corresponding control strategies based on the risk level, safety management of the workbench production process can be achieved, reducing the adverse impact of environmental risks on production safety.

[0038] In one example, based on the above embodiments, this embodiment further explains the method of collecting multiple environmental elements and constructing the environmental data model in S1. The multiple environmental elements include, but are not limited to, one or more of the following: temperature parameters, humidity parameters, dust concentration parameters, toxic or combustible gas concentration parameters, noise intensity parameters, illuminance parameters, and airflow parameters. Specifically, the temperature parameter reflects the thermal state of the environment surrounding the workbench; the humidity parameter reflects the ambient air humidity level; the dust concentration parameter reflects the content of suspended particulate matter in the air; the toxic or combustible gas concentration parameter reflects potential gas safety risks in the working environment; the noise intensity parameter reflects the acoustic environment state generated during workbench operation; the illuminance parameter reflects the lighting conditions of the working area; and the airflow parameter reflects the ambient airflow. The above environmental elements can be selected and combined according to the actual safety management needs of different production lines, and different workbenches can be configured with the same or different types of environmental sensors.

[0039] After collecting the raw environmental data corresponding to each environmental element, the environmental data is uniformly modeled to reduce preprocessing complexity. In this example, the environmental data model is represented in the form of a multi-dimensional vector, where each dimension corresponds to an environmental element, and different dimensions are used to carry the real-time data sequence of the corresponding environmental element.

[0040] Specifically, such as Figure 2As shown, S101: Under the same time reference, data on environmental elements such as temperature, humidity, dust concentration, toxic or combustible gas concentration, noise intensity, illuminance, and airflow parameters are combined according to a preset dimensional order to construct a multi-dimensional environmental data vector. S102: The data in each dimension are updated over time to form a real-time data sequence reflecting the dynamic changes in the environmental state. Data collected by different sensors are aligned in the time dimension to avoid misalignment or misjudgment in the fusion calculation.

[0041] By modeling data of multiple environmental elements in the form of multi-dimensional vectors, different environmental elements can be described under a unified data structure.

[0042] In one example, based on the above embodiment, this example further explains the method for extracting state feature parameters in step S2. The state feature parameters are not calculated based on environmental data at a single moment, but rather on environmental data within a preset time window in the environmental data model. The preset time window is a continuous time interval, the length of which can be set according to specific production scenarios and risk response needs, such as several seconds, tens of seconds, or several minutes. By selecting continuous environmental data within the preset time window, the changes in environmental elements over a period of time can be more comprehensively reflected, avoiding misjudgments caused by instantaneous abnormal fluctuations.

[0043] After selecting environmental data within a preset time window, feature extraction is performed on the environmental data to obtain state feature parameters corresponding to the environmental elements. In this example, the state feature parameters include one or more of the following: current state parameters, trend feature parameters, and fluctuation feature parameters. The current state parameter characterizes the actual state level of the environmental element at the current time node or the end of the time window, and can be calculated by taking the end value or weighted average of the environmental data within the time window. The trend feature parameter characterizes the changing trend of the environmental element within the preset time window, reflecting whether the environmental element is in an upward, downward, or relatively stable state. The trend feature parameter can reflect the evolution direction of environmental risk, providing trend information for subsequent risk fusion and evolution analysis. The fluctuation feature parameter characterizes the degree of fluctuation of the environmental element within the preset time window, reflecting the stability of the environmental element's changes. When the fluctuation amplitude is large, it indicates that the environmental state is unstable and there may be potential safety risks.

[0044] In this example, one or more state characteristic parameters can be extracted for different environmental elements. For example, for safety-sensitive environmental elements such as the concentration of toxic or flammable gases, both current state parameters and trend characteristic parameters can be extracted simultaneously; for environmental elements that are prone to fluctuations, such as noise intensity and airflow parameters, the fluctuation characteristic parameters can be extracted in particular.

[0045] By extracting multi-type state feature parameters based on a unified time window, subsequent multi-environmental element fusion calculations can simultaneously consider the real-time state, changing trends, and stability of environmental elements.

[0046] In one example, based on the above embodiments, this example further illustrates the specific calculation method of the fluctuation characteristic parameter. The fluctuation characteristic parameter can be obtained by calculating the variation amplitude of environmental factors within the preset time window.

[0047] like Figure 3 As shown, S201: Suppose that within a preset time window, the environmental data sequence corresponding to a certain environmental element is as follows: ; in, This represents the environmental element value corresponding to the nth sampling time within the preset time window; S202: The magnitude of change of this environmental element can be expressed as: ; max(·) represents taking the maximum value in the environmental data sequence, and min(·) represents taking the minimum value in the environmental data sequence. The change range A is used to characterize the maximum fluctuation range of the environmental element within a preset time window. The larger the change range, the more drastic the change in the environmental state, and the higher the corresponding safety risk.

[0048] In another example, the fluctuation characteristic parameter can be obtained by calculating the dispersion of environmental factors within the preset time window. For example, the standard deviation can be used as a measure of dispersion, such as... Figure 4 As shown, S211: First, calculate the average value of the environmental element within a preset time window. The calculation formula is as follows: ; S212: Recalculate the standard deviation, the formula for which is: ; in, Indicates the first The environmental element values ​​corresponding to each sampling time point, where n represents the number of sampling points within the preset time window.

[0049] The standard deviation It is used to reflect the fluctuation of environmental element data around the average value. When the standard deviation is large, it indicates that the environmental element is unstable and there is a potential risk of anomalies.

[0050] In a further embodiment of this example, to eliminate the impact of differences in the dimensions and value ranges of different environmental elements on the fusion calculation, the fluctuation characteristic parameters can be normalized. For example, a relative fluctuation coefficient can be used, the calculation formula of which is: .

[0051] In one example, building upon the above embodiment, this example further introduces a weighting step for different environmental factors before step S3. Based on the differences in the degree of impact of different environmental factors on safe production, corresponding weights are assigned to each environmental factor. These weights are used to characterize the relative importance of different environmental factors in the comprehensive risk assessment.

[0052] The weights can be preset based on one or more of the following factors, including the degree of direct impact of environmental factors on personal safety, the historical frequency of accidents caused by environmental factors, the hazard level of environmental factors in specific production scenarios, and the degree of attention paid to the environmental factor in industry safety standards or management experience. For example, for high-risk environmental factors such as the concentration of toxic or flammable gases, their weights can be set higher than those of general environmental factors such as temperature and humidity; for environmental factors such as dust concentration and noise intensity that may cause occupational hazards in specific scenarios, their weights can be set to a medium level.

[0053] In one example, based on the above embodiment, this example further explains the calculation method of the fused risk parameter in step S3. The fused risk parameter is obtained by weighting the state characteristic parameters of each environmental element with their corresponding weights. Specifically, in step S2, the corresponding state characteristic parameters have been extracted for different environmental elements. In step S3, the environmental element weights preset before step S3 are introduced to weight and fuse the state characteristic parameters, thereby forming a fused risk parameter that can comprehensively reflect the safety risk level of the current workstation.

[0054] like Figure 5 As shown, S301: Assume that the environmental elements participating in the fusion calculation total [number missing]. There are 1, and the corresponding state feature parameters are as follows: ; in, Indicates the first The state characteristic parameters corresponding to each environmental element may include one or more of the following: current state parameters, trend characteristic parameters, or fluctuation characteristic parameters. This indicates the number of environmental elements participating in the fusion calculation.

[0055] S302: Correspondingly, a weight is pre-assigned for each environmental element: ; in, Indicates the first The weights of each environmental element are used to characterize the degree of impact of that environmental element on safe production. Each weight can be a positive number and can be normalized as needed.

[0056] In this example, the pre-set weights are based on the degree of production impact of each environmental element on safety accidents in historical production data. The degree of production impact is determined by analyzing one or more of the following factors: the correlation strength between each environmental element and the safety accident, the frequency of occurrence, and the severity of the accident.

[0057] In one approach, statistical analysis of historical production data is used to determine the correlation strength between changes in various environmental factors and the occurrence of safety accidents, and this correlation serves as a reference for weighting. The correlation strength can be determined by the ratio of the number of accidents occurring when an environmental factor is in an abnormal state to the total number of times an environmental factor is in an abnormal state. The correlation strength reflects the degree to which the probability of a corresponding safety accident increases when a certain environmental factor is in an abnormal state; the higher the correlation strength, the more significant the impact of that environmental factor on safety accidents, and the greater its corresponding weight should be.

[0058] Alternatively, the frequency of safety accidents caused by abnormal states of different environmental factors during historical production processes can be statistically analyzed, and weights can be set based on the frequency of occurrence. Specifically, the frequency of occurrence can be determined by the ratio of the total number of accidents corresponding to abnormal states of environmental factors to the total number of production cycles. If an environmental factor shows abnormalities multiple times in historical production data and is frequently accompanied by safety accidents, then the environmental factor is determined to be a high-frequency risk factor, and its corresponding weight is increased; conversely, if an environmental factor shows abnormalities but rarely causes accidents, its corresponding weight is relatively decreased.

[0059] In another scenario, the weights can be adjusted based on the severity of safety accidents caused by different environmental factors. The severity of the accident can be assessed based on one or more of the following indicators: whether it causes personal injury, whether it causes equipment downtime or damage, whether it causes production line interruption or significant economic loss. For example, it can be represented by a numerical value of 0-1. When an abnormality of a certain environmental factor is usually accompanied by a higher degree of accident severity, the corresponding weight is set to a higher value to highlight its impact in the integrated risk calculation.

[0060] Alternatively, the weights can be obtained by weighting and comprehensively calculating the correlation strength, frequency of occurrence, and severity of accidents obtained above. The weighting coefficients can be adjusted according to the enterprise's safety management strategy. Through the above comprehensive weight setting method, the weights of this application can reflect the actual risk contribution of different environmental factors in historical production scenarios, rather than relying solely on fixed empirical values ​​or single thresholds. This makes the subsequent fusion risk calculation more consistent with the safety risk distribution characteristics in real production environments.

[0061] S303: The risk parameter of multiple environmental factors can be calculated by weighted summation, and the calculation formula is as follows: ; in, Indicates the first The weights of each environmental element are used to characterize the relative degree of their impact on safe production. Indicates the first The state characteristic parameters corresponding to each environmental element may include one or more of the following: current state parameters, trend characteristic parameters, or fluctuation characteristic parameters. This indicates the number of environmental elements participating in the fusion calculation.

[0062] In one optional implementation, when an environmental element corresponds to multiple state characteristic parameters, the multiple state characteristic parameters of the environmental element can be internally combined first, and then weighted and calculated with corresponding weights. Specifically, corresponding coefficients are set for different types of state characteristic parameters, and a comprehensive state characteristic parameter of the environmental element is constructed through the coefficients. Then, the comprehensive state characteristic parameter is introduced into the weighted calculation of the fusion risk parameter.

[0063] In one example, the method of setting weights for different environmental elements is further improved by introducing a coupling risk correlation mechanism between environmental elements. In this example, in addition to pre-setting weights for different environmental elements, the correlation between multiple environmental elements is also analyzed. For example... Figure 6 As shown, S311: Determine whether at least two environmental elements simultaneously meet the preset association conditions within the same time period. If so, S312: Determine that there is a coupled risk association between the environmental elements. The coupled risk association is used to characterize the situation where multiple environmental elements exhibit coordinated anomalies in terms of time and state changes. Such coordinated anomalies may amplify the impact of a single environmental element on safe production.

[0064] S313: After determining that there is a coupled risk correlation among the environmental elements, the weight of the environmental elements with coupled risk correlation is amplified in the fusion calculation. Specifically, let the weight of a certain environmental element be... When determining that an environmental element has a coupled risk association with at least one other environmental element, its weight is adjusted as follows: ; in, This indicates the weight of the environmental element. This represents the amplified weight. This represents the weight amplification factor, and .

[0065] By amplifying the weight of environmental elements with coupled risk relationships, the environmental elements occupy a higher proportion in the calculation of integrated risk parameters, thereby improving the system's sensitivity to multi-factor collaborative abnormal risks.

[0066] Based on the above embodiments, this example further specifies the preset association conditions to clarify the criteria for determining the coupling risk association. In this example, the preset association conditions include at least two environmental elements whose changes within the same time period exceed corresponding change thresholds. The change range of each environmental element can be calculated based on the difference between its maximum and minimum values ​​within a preset time window; the corresponding change threshold can be preset based on the safety standards, historical data, or management experience of that environmental element.

[0067] Only when the changes in multiple environmental factors simultaneously exceed their respective change thresholds are the changes considered significant, thus meeting the basic conditions for participating in coupled risk assessment.

[0068] In this example, the preset association condition further includes: the changes of the at least two environmental elements occur within a preset time tolerance. The time tolerance is used to limit the proximity of the time at which different environmental elements undergo significant changes. For example, when the time difference between the changes of two environmental elements is less than the preset time tolerance, they are considered to be synchronous in the time dimension. By introducing the time tolerance condition, the misjudgment of temporally independent environmental changes as coupled risk associations is avoided, thereby improving the accuracy of coupling judgment.

[0069] A joint determination mechanism is also provided, which determines that the environmental elements meet the preset correlation conditions only when at least two environmental elements simultaneously meet the change magnitude threshold condition and the time tolerance condition, and further triggers the coupling risk correlation determination and weight amplification processing.

[0070] In a specific application example, this is applied to a single production line in an electronic assembly workshop. The production line has the problem of fire risk caused by the superposition of temperature rise, dust and flammable gas. The goal is to identify high-risk workstations 5 minutes in advance and intervene automatically.

[0071] Multiple environmental sensors are deployed on each workbench to collect data on various environmental factors, including temperature, humidity, dust concentration, toxic gas concentration, noise intensity, illuminance, and airflow parameters. Each environmental factor is sampled at a frequency of 1 Hz, and anomaly thresholds are set for each factor: temperature > 50℃, humidity > 70%, dust concentration > 100 mg / m³, combustible gas concentration > 50 ppm, noise intensity > 85 dB, illuminance < 300 lx, and airflow parameter < 0.3 m / s.

[0072] Using a 5-minute time window, synchronize the data from each sensor according to the timestamp, within the time window [ Within this time window, an environmental data model is formed for each time window, where each environmental element has 300 sampling points within the time window.

[0073] ; Within each time window, state characteristic parameters are extracted from the environmental data model, including current state parameters, trend characteristic parameters, and trend feature parameters. The current state parameters are the values ​​of environmental elements at the end of the window, such as a current temperature of 49.8℃ and a dust concentration of 96 mg / m³. 3 The concentration of combustible gas was 41 ppm.

[0074] The rate of change of environmental elements is calculated using the window beginning-end difference method, and this rate of change is used as a trend characteristic parameter. For example, the rate of change of temperature is as follows: ; Where 49.8 is the temperature value at the end of the window, and 45.2 is the temperature value at the beginning of the window; The dust change rate is: ; Where 96 is the dust concentration value at the end of the window, and 60 is the dust concentration value at the beginning of the window; The rate of gas change is: ; Where 41 is the value of the combustible gas concentration at the end of the window, and 20 is the value of the combustible gas concentration at the beginning of the window. The fluctuation characteristic parameter is obtained by calculating the standard deviation of environmental factors within the window. The calculation formula has been shown in the above embodiment and will not be repeated in this example. The calculation result is shown in the example below: , , .

[0075] Normalization is performed based on the abnormal threshold. For some exemplary environmental elements, the abnormal threshold for temperature is 50°C, the current value is 49°C, and the normalized value is 0.996; the abnormal threshold for dust concentration is 100 mg / m³, the current value is 96 mg / m³, and the normalized value is 0.96; the abnormal threshold for combustible gas concentration is 50 ppm, the current value is 41 ppm, and the normalized value is 0.82.

[0076] Historical production data and safety accident records from the past 12 months were collected, resulting in: a total production operation time of 8640 hours, 126 valid safety events, and 18 confirmed accidents. The correlation strength C, accident frequency F, and accident severity S for each environmental element were calculated. Taking temperature as an example, there were 312 periods of abnormal temperature. Within 10 minutes of an abnormal temperature event, 203 accidents occurred. Therefore, the correlation strength of temperature is: ; Similarly, the correlation strength of the dust particles can be obtained as follows: The correlation strength between the flammable gas concentration and the concentration is: ; The statistics show a total of 18 accidents over 12 months. The number of times each environmental element was anomaly was analyzed among these accidents. For example, temperature was involved in 6 accidents, dust concentration in 8, and combustible gas concentration in 4. The accident frequency for each environmental element was calculated, including temperature. Dust concentration Combustible gas concentration .

[0077] The severity of an accident is comprehensively assessed based on three indicators: downtime (min), personal injury level (level 1-3), and economic loss (ten thousand yuan). According to the company's pre-set rules based on production experience, the coefficient for downtime is 0.4, the coefficient for personal injury level is 0.3, and the coefficient for economic loss is 0.3. Therefore, the formula for scoring the severity of a single accident is: ; The downtime is normalized as: downtime / 240, and the economic loss is normalized as: loss amount / 50.

[0078] The severity of accidents involving these environmental factors is statistically analyzed. Some exemplary environmental factors are temperature (0.55), dust concentration (0.62), and combustible gas concentration (0.88).

[0079] The weights of each environmental element are calculated comprehensively according to preset proportions α, β, and γ: ; α, β, and γ can be set according to the company's security management strategy, for example, α=0.5, β=0.3, and γ=0.2.

[0080] Based on the above data, the temperature was calculated to be... Dust concentration Combustible gas concentration .

[0081] In one method for determining coupling risk, a coupling of time tolerance and amplitude is adopted. Three judgment conditions are set as follows: temperature change rate > 0.01 ℃ / s, dust change rate > 0.1 mg / m³ / s, and time tolerance Δt ≤ 60s. The actual observed data in this example are: temperature anomaly time: t = 240 s, dust concentration anomaly time: t = 255 s. Calculating |240 - 255| = 15 s ≤ 60 s, the risk is determined to be temperature-dust coupling risk.

[0082] The weights are amplified by a factor of 1.2, and the temperature is updated to reflect this. Dust concentration Combustible gas concentration .

[0083] Substituting the numerical calculation fusion risk parameters: ; To calculate the risk evolution trend, the two most recent windows are calculated, which are 0.81 and 0.925 respectively. The rate of change is then... The predicted fusion risk parameter after 5 minutes is: 0.925 + 0.00038 × 300 = 1.039.

[0084] Three risk levels are set: when the R value is less than 0.5, the risk level is low; when the R value is between 0.5 and 0.8, the risk level is medium; and when the R value is greater than 0.8, the risk level is high. The current R value is 0.925, the real-time risk level is high, and the predicted risk continues to rise.

[0085] The corresponding control strategies include stopping the current workbench, activating the forced ventilation device, triggering audible and visual alarms, and pushing risk information to the central control system.

[0086] This embodiment provides a workbench production line control system based on environmental condition analysis. This system, through the collaborative work of multiple modules, achieves real-time perception, risk assessment, trend prediction, and proactive control of the workbench production environment. For example... Figure 7As shown, the system includes at least an environmental data acquisition module 11, a data modeling module 12, a feature extraction module 13, a risk fusion calculation module 14, a risk evolution analysis module 15, an anomaly identification and risk classification module 16, and a control strategy execution module 17.

[0087] The environmental data acquisition module 11 is configured to arrange various environmental sensors on each workbench for collecting data on multiple environmental elements. Specifically, the environmental sensors may include one or more of the following: temperature sensor, humidity sensor, dust concentration sensor, toxic or combustible gas sensor, noise sensor, illuminance sensor, and airflow sensor. Each environmental sensor is connected to the environmental data acquisition module via wired or wireless means.

[0088] The environmental data acquisition module 11 can acquire real-time data of various environmental elements according to a preset sampling period, and perform preliminary formatting processing on the acquired data for subsequent module calls.

[0089] The data modeling module 12 is communicatively connected to the environmental data acquisition module 11 and is configured to perform unified modeling on the acquired environmental data to form an environmental data model. In this embodiment, the data modeling module 12 performs time synchronization processing on environmental data from different types of sensors and maps the synchronized data to a unified data structure, so that the environmental data model simultaneously includes both time and environmental element dimensions.

[0090] Through unified modeling, data from different environmental elements are expressed consistently at the structural level, providing a unified data foundation for feature extraction and risk analysis.

[0091] The feature extraction module 13 is communicatively connected to the data modeling module 12 and is configured to extract features from the environmental data model 12 to obtain the state feature parameters corresponding to each environmental element.

[0092] In this embodiment, the feature extraction module 13 extracts one or more of the current state feature parameters, trend feature parameters, and fluctuation feature parameters of each environmental element from the environmental data model based on a preset time window, so as to comprehensively characterize the operating status of the environmental element within the time window.

[0093] The risk fusion calculation module 14 is communicatively connected to the feature extraction module 13 and is configured to perform fusion calculations on multiple environmental elements based on the state feature parameters to generate fusion risk parameters that characterize the risk level of the current workstation.

[0094] In this embodiment, the risk fusion calculation module 14 sets basic weights for different environmental elements, and when multiple environmental elements are detected to meet preset association conditions, the weights of environmental elements with coupled risk associations are dynamically amplified, thereby highlighting the impact of multi-element collaborative anomalies on the risk level.

[0095] The integrated risk parameters are used to comprehensively reflect the overall risk level of the current workstation under the combined influence of multiple environmental factors.

[0096] The risk evolution analysis module 15 is communicatively connected to the data modeling module 12 and the risk fusion calculation module 14. It is configured to calculate the evolution trend of risk level over time based on the environmental data model and fused risk parameters, and obtain the risk evolution results within the prediction period.

[0097] In this embodiment, the risk evolution analysis module 15 can combine the historical changes of the integrated risk parameters to analyze the direction and rate of change of the risk level, thereby predicting the development trend of workstation risk in the future and providing a basis for early intervention.

[0098] The anomaly identification and risk classification module 16 is communicatively connected to the risk evolution analysis module 15 and is configured to identify abnormal environmental conditions based on the risk evolution results and determine the corresponding risk level.

[0099] In this embodiment, the anomaly identification and risk classification module 16 compares the predicted risk evolution results with the preset risk threshold, and classifies the current or predicted risk status into different risk levels, such as normal level, warning level and high risk level, based on the comparison results.

[0100] The control strategy execution module 17 is communicatively connected to the anomaly identification and risk classification module 16 and is configured to trigger the corresponding control strategy according to the risk level in order to control the operating status of the workbench equipment.

[0101] In this embodiment, when the risk level reaches the warning level or the high-risk level, the control strategy execution module 17 can send control commands to the relevant workbench equipment or production line control system to perform operations such as reducing the equipment operating speed, starting the ventilation and dust removal equipment, issuing audible and visual alarms, or suspending production, thereby reducing the risk of safe production.

[0102] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A workbench production line control method based on environmental condition analysis, characterized in that, include: S1: Various environmental sensors are arranged on each workbench to collect multiple environmental elements through the environmental sensors, and the collected environmental data is uniformly modeled to obtain an environmental data model. S2: Perform feature extraction on the environmental data model to extract the state feature parameters corresponding to each environmental element; S3: Based on the state characteristic parameters, multiple environmental elements are fused and calculated to obtain fused risk parameters that characterize the current workstation risk level; S4: Based on the environmental data model and fused risk parameters, calculate the evolution trend of risk level over time to obtain the risk evolution results within the prediction period; S5: Based on the risk evolution results, identify abnormal environmental conditions and determine the corresponding risk levels; S6: Based on the risk level, trigger the corresponding control strategy to control the operating status of the workbench equipment.

2. The method according to claim 1, characterized in that, S1 includes: The multiple environmental factors include one or more of the following: temperature, humidity, dust concentration, toxic or combustible gas concentration, noise intensity, illuminance, and airflow parameters. The environmental data model is represented in the form of a multi-dimensional vector, where different dimensions correspond to real-time data sequences of different environmental elements.

3. The method according to claim 1, characterized in that, The process of uniformly modeling the collected environmental data includes: Environmental data from different environmental sensors are timestamped and resampled and time-aligned according to a preset time window; The time-aligned multi-environmental element data is organized by time slices and mapped to a unified data structure. The unified data structure represents the temporal relationship of environmental data in the time dimension and the state distribution of different environmental elements in the environmental element dimension, thereby forming an environmental data model jointly expressed by multiple environmental elements.

4. The method according to claim 1, characterized in that, S2 include: The state feature parameters are calculated based on environmental data within a preset time window in the environmental data model, and the state feature parameters include one or more of the following: current state parameters, trend feature parameters, and fluctuation feature parameters.

5. The method according to claim 4, characterized in that, The fluctuation characteristic parameter is calculated based on continuous sampling data of each environmental element within the preset time window. The fluctuation characteristic parameter is used to reflect at least the change range and numerical dispersion of the corresponding environmental element within the preset time window. The change range is used to characterize the extreme value change range of the environmental element value, and the dispersion is used to characterize the degree of fluctuation dispersion of the environmental element value relative to its statistical mean.

6. The method according to claim 1, characterized in that, Prior to S3, it also included: Weights are assigned to different environmental factors, and these weights are pre-set based on one or more of the following: the correlation strength, frequency of occurrence, and severity of accidents between each environmental factor and the occurrence of safety accidents in historical production data.

7. The method according to claim 6, characterized in that, S3 includes: The state characteristic parameters corresponding to each environmental element are matched with their corresponding weights, and the state characteristic parameters are weighted and fused based on the weights to obtain the fused risk parameters that characterize the overall risk level of the current workstation.

8. The method according to claim 6, characterized in that, Setting weights for different environmental factors includes: When at least two environmental elements meet the preset association conditions within the same time period, it is determined that there is a coupling risk association between the environmental elements. When a coupling risk association is determined, the weight of the corresponding environmental element in the fusion calculation is amplified.

9. The method according to claim 8, characterized in that, The preset association conditions include: The changes in at least two environmental elements within the same time period both exceed the corresponding change thresholds, and the changes in at least two environmental elements occur within a preset time tolerance.

10. A workbench production line control system based on environmental condition analysis, using the method described in any one of claims 1-9, characterized in that, include: The environmental data acquisition module is configured to deploy various environmental sensors on each workbench and collect data on multiple environmental elements through the environmental sensors. The data modeling module is configured to perform unified modeling of the collected environmental data to form an environmental data model. The feature extraction module is configured to extract features from the environmental data model to obtain state feature parameters corresponding to each environmental element. The risk fusion calculation module is configured to perform fusion calculations on multiple environmental elements based on the state characteristic parameters to generate fusion risk parameters that characterize the risk level of the current workstation. The risk evolution analysis module is configured to calculate the evolution trend of risk level over time based on the environmental data model and fused risk parameters, and obtain the risk evolution results within the prediction period. The anomaly identification and risk classification module is configured to identify abnormal environmental conditions based on the risk evolution results and determine the corresponding risk level. The control strategy execution module is configured to trigger the corresponding control strategy according to the risk level in order to control the operating status of the workbench equipment.

Images