Electric energy meter assembly quality detection method and electric energy meter production environment control system

Abstract

The application provides an electric energy meter assembly quality detection method and an electric energy meter production environment control system, and relates to the technical field of electric energy meters. The method comprises the following steps: for each detection area, determining the adjustment information corresponding to each environment regulation and control device in the detection area according to the environment parameters and environment context information collected by each environment parameter collection device in the detection area, and sending the corresponding first control instruction to each environment regulation and control device. The actual assembly image of at least one key assembly point in the assembly process corresponding to each detection area is detected, an assembly quality detection result is generated, at least one target adjustment parameter item is determined according to the assembly quality detection result, and the value of the target adjustment parameter item is adjusted by sending a second control instruction to the environment regulation and control device corresponding to the target adjustment parameter item. The double mechanism of active adjustment and continuous quality inspection feedback is adopted to comprehensively improve the stability, yield rate and intelligent level of the electric energy meter assembly process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electric energy meter, in particular to an electric energy meter assembly quality detection method and an electric energy meter production environment control system. BACKGROUND

[0002] In the production and assembly process of the electric energy meter, since the electric energy meter contains some precise components inside, the precise components are extremely sensitive to the assembly environment, especially under the condition of large temperature, humidity and air pressure fluctuations, assembly defects are prone to occur.

[0003] In the prior art, the temperature, humidity and air pressure data in the production workshop are usually monitored in real time by sensors, and then an operator determines whether the sensor data exceeds the threshold value according to the test, and manually intervenes and manually adjusts the parameters of the related equipment in the production workshop when the threshold value is exceeded. The above-mentioned method can realize basic environment monitoring, but the entire adjustment process relies on manual intervention, the response efficiency is poor, and the electric energy meter has assembly defects. In addition, due to the existence of environmental fluctuations, subsequent assembly quality detection is prone to misjudgment due to environmental interference, thereby affecting the accuracy of the assembly quality determination. SUMMARY

[0004] The purpose of the present application is to solve the problems of low parameter adjustment response efficiency, easy existence of assembly defects and difficulty in accurately determining the assembly quality in the prior art by providing an electric energy meter assembly quality detection method and an electric energy meter production environment control system.

[0005] To achieve the above-mentioned purpose, the technical solutions adopted by the embodiments of the present application are as follows:

[0006] In a first aspect, the embodiments of the present application provide an electric energy meter assembly quality detection method applied to a controller in an electric energy meter production environment control system, the system comprising: the controller, a plurality of environment regulation devices arranged in each detection area, and an environment parameter acquisition device corresponding to each environment regulation device, the detection area being determined by dividing the production area of the electric energy meter according to the assembly process information of the electric energy meter, and the method comprising:

[0007] Obtaining the environment parameters collected by each environment parameter acquisition device in each detection area;

[0008] For each detection area, determining the adjustment information corresponding to each environment regulation device in the detection area according to the environment parameters collected by each environment parameter acquisition device in the detection area and the environmental context information, and sending the corresponding first control instruction to each environment regulation device, so that each environment regulation device adjusts the production environment of the detection area according to the adjustment information contained in the first control instruction;

[0009] The actual assembly image of at least one key assembly point in the assembly process corresponding to each detection area is obtained, and image detection is performed on the actual assembly image of at least one key assembly point in the assembly process corresponding to each detection area to generate an assembly quality detection result. The assembly quality detection result is used to indicate whether the energy meter has assembly defects caused by changes in environmental parameters.

[0010] Based on the assembly quality inspection results, at least one target adjustment parameter is determined, and the value of the target adjustment parameter is adjusted by sending a second control command to the environmental control equipment corresponding to each target adjustment parameter.

[0011] As one possible implementation, determining the adjustment information corresponding to each environmental control device within the detection area based on the environmental parameters collected by each environmental parameter acquisition device within the detection area and the environmental context information includes:

[0012] Based on the environmental parameters collected by each environmental parameter acquisition device within the detection area, external environmental information, response characteristics of each environmental parameter acquisition device, control logic rules of the assembly process corresponding to the detection area, and preset energy consumption strategies, the adjustment information corresponding to each environmental control device within the detection area is determined.

[0013] As one possible implementation, determining the adjustment information corresponding to each environmental control device within the detection area based on the environmental parameters collected by each environmental parameter acquisition device within the detection area, external environmental information, the response characteristics of each environmental parameter acquisition device, the control logic rules of the assembly process corresponding to the detection area, and a preset energy consumption strategy includes:

[0014] Based on the external environment information, the response characteristics of each of the environmental parameter acquisition devices, the control logic rules of the assembly process corresponding to the detection area, and the preset energy consumption strategy, the target environmental parameters of the detection area are determined.

[0015] Based on the environmental parameters collected by each of the environmental parameter acquisition devices and the target environmental parameters of the detection area, the environmental parameter change information of each of the environmental parameter acquisition devices is determined. The environmental parameter change information includes: deviation and change trend.

[0016] Based on the response characteristics of each environmental parameter acquisition device and the environmental parameter change information, the corresponding adjustment information for each environmental control device is determined.

[0017] As one possible implementation, determining the target environmental parameters of the detection area based on the external environment information, the response characteristics of each of the environmental parameter acquisition devices, the control logic rules of the assembly process corresponding to the detection area, and the preset energy consumption strategy includes:

[0018] The external environmental information, the response characteristics of each of the environmental parameter acquisition devices, the control logic rules of the assembly process corresponding to the detection area, and the preset energy consumption strategy are input into a pre-trained environmental decision model. Based on the control logic rules of the assembly process corresponding to the detection area, the environmental decision model determines the theoretical value and tolerance range of the environmental parameters. Then, based on the external environmental information, the response characteristics of each of the environmental parameter acquisition devices, the preset energy consumption strategy, and the tolerance range, the theoretical value of the environmental parameters is adjusted to obtain the target environmental parameters.

[0019] As one possible implementation, the step of performing image detection on the actual assembly image of at least one key assembly point in the assembly process corresponding to each of the detection areas to generate an assembly quality inspection result includes:

[0020] For each of the aforementioned detection areas, standard assembly images of each of the aforementioned key assembly points within the detection area are obtained, along with annotation information for the standard assembly images. The annotation information includes a first key feature region and an allowable error range.

[0021] For each of the key assembly points, the actual assembly image of the key assembly point is aligned with the standard assembly image to obtain a processed assembly image. Based on the annotation information of the standard assembly image, image detection is performed on the processed assembly image to generate the detection result of the key assembly point.

[0022] The assembly quality inspection result is generated based on the inspection results of each key assembly point within each inspection area.

[0023] As one possible implementation, the step of performing image detection on the processed assembly image based on the annotation information of the standard assembly image to obtain the detection results of the key assembly points includes:

[0024] Based on the first key feature region of the standard assembly image, determine the second key feature region of the processed assembly image;

[0025] Difference detection is performed on the first key feature region and the second key feature region to obtain an initial difference detection result. Based on the initial difference detection result and the allowable error range, the detection result of the key assembly point is generated.

[0026] As one possible implementation, the detection area is determined according to the following steps:

[0027] According to the assembly process of the electricity meter, the production area of ​​the electricity meter is divided into multiple functional areas, and each functional area corresponds to an assembly process.

[0028] The influence weight of each functional area is determined based on the degree of influence of the assembly process corresponding to each functional area on the assembly quality of the electricity meter.

[0029] The functional area with an influence weight greater than a preset value is designated as the detection area.

[0030] As one possible implementation, determining at least one target adjustment parameter based on the assembly quality inspection results includes:

[0031] If the assembly quality inspection result indicates that the energy meter has assembly defects, then the target inspection area where the assembly defects occur is determined, and the historical assembly environment parameters of the target inspection area are obtained.

[0032] Based on the historical assembly environment parameters of the target detection area, at least one target adjustment parameter item is determined from the mapping relationship table, wherein the mapping relationship table is used to indicate the correlation between various assembly defects and environmental parameters that affect assembly.

[0033] As one possible implementation, it also includes:

[0034] Obtain a sample dataset, which includes first assembly environment parameters of multiple defect-free energy meters and second assembly environment parameters of multiple defective energy meters.

[0035] The sample dataset is input into the pre-trained prediction model. Multiple first parameter combinations are determined based on the sample dataset, and each first parameter combination is traversed. For the currently traversed first parameter combination, the defect probability of the first parameter combination is determined.

[0036] Based on the defect probability of each first parameter combination, determine the range of optimization parameters, and determine multiple second parameter combinations within the range of optimization parameters and the energy consumption information corresponding to each second parameter combination;

[0037] Based on the energy consumption information corresponding to each of the second parameter combinations, the target parameter combination is selected from multiple second parameter combinations.

[0038] Secondly, this application provides an energy meter production environment control system, the system including: a controller, multiple environmental control devices installed in each detection area, and environmental parameter acquisition devices corresponding to each environmental control device;

[0039] Each of the environmental control devices and each of the environmental parameter acquisition devices is connected to the controller;

[0040] The controller is used to perform the steps in the method for inspecting the assembly quality of an energy meter as described in any one of the first aspects.

[0041] Thirdly, embodiments of this application provide a controller, including: a processor, a storage medium, and a bus. The storage medium stores machine-readable instructions executable by the processor. When the controller is running, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the electricity meter assembly quality inspection method as described in any of the first aspects above.

[0042] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the electricity meter assembly quality inspection method as described in any of the first aspects above.

[0043] According to the electricity meter assembly quality inspection method and electricity meter production environment control system of the embodiments of this application, based on the real-time environmental parameters and environmental context information of each detection area, the controller dynamically generates and issues a first control command to achieve rapid and accurate control of key parameters such as temperature, humidity, and air pressure, significantly improving the response speed and pertinence of environmental regulation. Furthermore, by acquiring actual assembly images of key assembly points and performing high-precision image detection, subtle assembly defects caused by environmental fluctuations can be objectively and quantitatively identified, overcoming the shortcomings of subjective judgment and high false negative rate in manual judgment. The assembly quality inspection results are used to drive the generation of a second control command, dynamically optimizing the environmental parameter settings and forming a quality feedback closed loop, thereby comprehensively improving the stability, yield, and intelligence level of the electricity meter assembly process. In other words, according to the embodiments of this application, on the one hand, the controller rapidly generates and issues a first control command based on real-time environmental parameters and environmental context information, realizing single-time active adjustment of the environmental control equipment in each detection area, significantly improving the response speed of the environmental parameter acquisition equipment and the control accuracy of the environmental control equipment, reducing assembly risks caused by deviations in temperature, humidity, and air pressure from the source. On the other hand, by continuously acquiring actual assembly images at key processes and performing re-execution image inspections, dynamic and high-precision monitoring of assembly quality is achieved. The inspection results are used as feedback signals to generate second control commands, dynamically optimizing environmental parameter settings and realizing quality-driven closed-loop adaptive control. This dual mechanism of proactive adjustment and continuous quality inspection feedback ensures the immediacy of environmental control while suppressing assembly defects through iterative optimization. Furthermore, visual data supports objective quality judgment, overcoming the shortcomings of traditional methods that rely on human experience, have slow response times, and are difficult to trace, thus comprehensively improving the stability and intelligence level of electricity meter assembly. Attached Figure Description

[0044] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 A schematic diagram of the architecture of an energy meter production environment control system provided in an embodiment of this application is shown;

[0046] Figure 2 A flowchart illustrating a method for quality testing of electricity meter equipment provided in an embodiment of this application is shown.

[0047] Figure 3 A flowchart illustrating a method for determining adjustment information provided in an embodiment of this application is shown;

[0048] Figure 4 A flowchart illustrating a method for generating assembly quality inspection results according to an embodiment of this application is shown.

[0049] Figure 5 A flowchart illustrating a parameter optimization method provided in an embodiment of this application is shown;

[0050] Figure 6 A schematic diagram of the structure of a controller provided in an embodiment of this application is shown. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0052] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0053] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0054] Figure 1 A schematic diagram of the architecture of a power meter production environment control system provided in an embodiment of this application is shown. (Refer to...) Figure 1 As shown, the energy meter production environment control system includes: a controller, multiple environmental control devices installed in each detection area, and environmental parameter acquisition devices corresponding to each environmental control device, and each environmental control device and each environmental parameter acquisition device are connected to the controller.

[0055] Optionally, the environmental parameter acquisition equipment includes: humidity acquisition equipment, temperature acquisition equipment, and air pressure detection equipment. Each environmental parameter acquisition equipment collects environmental parameters within the detection area in real time to monitor the production environment status of the detection area in real time and reports the collected environmental parameters to the controller.

[0056] Optionally, the environmental control equipment includes: humidifiers, air conditioning units corresponding to the air conditioning outlets, and air compressors. The controller can generate control commands and send corresponding control commands to each environmental control device, driving the humidifiers, air conditioning units corresponding to the air conditioning outlets, or air compressors to dynamically adjust environmental parameters, ensuring that key indicators such as temperature, humidity, and air pressure in each detection area remain stable within the process requirements, thereby effectively ensuring the quality stability and consistency of the electricity meter assembly process.

[0057] Optionally, the electricity meter production environment control system also includes multiple image acquisition devices installed in each inspection area. Each image acquisition device is located at a key assembly point within the inspection area. These devices are used to acquire assembly images at each key assembly point in real time during the electricity meter production assembly process and report these images to the controller in real time. The controller then performs image recognition based on these images to determine whether the electricity meter has assembly defects within the corresponding inspection area. Key assembly points refer to critical locations in the assembly process corresponding to each inspection area that significantly impact the assembly quality of the electricity meter, such as solder joints and connector points.

[0058] Based on this, the electricity meter production environment control system provided in this application, through centralized and coordinated control of environmental parameter acquisition equipment and environmental control equipment by the controller, realizes real-time monitoring, dynamic adjustment, and closed-loop optimization of the electricity meter production environment. It can accurately maintain key parameters such as temperature, humidity, and air pressure in each detection area within ideal ranges, effectively reducing the risk of assembly defects caused by environmental fluctuations. Simultaneously, the system supports intelligent decision-making based on quality feedback and energy consumption optimization, enabling energy-saving operation while ensuring the quality of electricity meter assembly. This significantly improves the stability, consistency, and energy efficiency of the production process, achieving the technical goals of high yield, high automation, and intelligent management in electricity meter manufacturing.

[0059] The following is in conjunction with the above. Figure 1 The contents described in the electricity meter production environment control system shown herein provide a detailed explanation of the electricity meter equipment quality testing method provided in the embodiments of this application.

[0060] Figure 2 This diagram illustrates a flowchart of a method for quality inspection of electricity meter equipment according to an embodiment of this application. The execution entity of this method is the controller in the aforementioned electricity meter production environment control system. (Refer to...) Figure 2As shown, the method specifically includes the following steps:

[0061] S201. Obtain the environmental parameters collected by the environmental parameter acquisition devices in each detection area.

[0062] Optionally, each detection area is equipped with multiple different types of environmental parameter acquisition devices, such as temperature acquisition devices for collecting ambient temperature, humidity acquisition devices for collecting relative humidity, and air pressure detection devices for collecting atmospheric pressure. Accordingly, the acquired environmental parameters include temperature, humidity, and air pressure. Each environmental parameter acquisition device is connected to the controller, and each device continuously collects environmental parameters at a certain sampling frequency and uploads the collected parameters to the controller.

[0063] Optionally, the testing area can be determined as follows: Based on the assembly process of the electricity meter, the production area of ​​the electricity meter is divided into multiple functional areas. The influence weight of each functional area is determined according to the degree of influence of the corresponding assembly process on the assembly quality of the electricity meter. Functional areas with influence weights greater than a preset value are designated as testing areas. Each functional area corresponds to one assembly process.

[0064] For example, the assembly process of an electricity meter refers to the complete manufacturing process of the electricity meter from raw materials to finished product. This process typically includes multiple assembly steps, such as surface mounting, welding, insertion, casing assembly, and sealing. In this application, based on the assembly process of the electricity meter, the production area of ​​the electricity meter is divided into multiple physical production areas, resulting in multiple functional areas, such as surface mounting area, welding area, insertion area, assembly area, and sealing area. That is, each functional area corresponds to one assembly step. Then, a quantitative index is used to measure the degree of influence of the assembly step in each functional area on the final product assembly quality, resulting in the influence weight of each functional area. The larger the influence weight value, the more critical the assembly step corresponding to that functional area is. Further, the influence weight of each functional area is compared with a preset value. Taking an influence weight with a maximum value of 1 as an example, the preset value can be set to, for example, 0.8. Only functional areas with influence weights greater than this preset value are considered as detection areas.

[0065] For example, the impact of assembly processes corresponding to each functional area on the assembly quality of the electricity meter can be determined by statistically analyzing the distribution of various assembly defects during historical production assembly processes. For instance, if 80% of the cold solder joints in historical production assembly processes occur in the welding area, then the welding area has a high weight in terms of its impact on the assembly quality of the electricity meter, and can be considered as a detection area. Alternatively, the impact of assembly processes corresponding to each functional area on the assembly quality of the electricity meter can also be determined through experience or experimental verification. Experimental verification can involve artificially changing the environmental parameters of a certain assembly process and observing the changes in the assembly defect rate, thereby quantifying the impact of the assembly process on the corresponding functional area.

[0066] S202. For each detection area, based on the environmental parameters collected by the environmental parameter acquisition devices in the detection area and the environmental context information, determine the corresponding adjustment information of each environmental control device in the detection area, and send the corresponding first control command to each environmental control device so that each environmental control device adjusts the production environment of the detection area according to the adjustment information contained in the first control command.

[0067] Optionally, environmental context information refers to information other than real-time collected environmental parameters, including some real-time or non-real-time information related to the current production environment control, but affecting the corresponding adjustment information of environmental control equipment. In this embodiment, for each detection area, the controller determines the current environment based on the environmental parameters collected by each environmental parameter acquisition device within the detection area, and combines the environmental context information to determine whether the current environment of the detection area deviates from the target, such as whether the temperature deviates from the preset temperature range, whether the humidity deviates from the preset humidity range, whether the air pressure deviates from the preset air pressure range, etc., and determines the adjustment information corresponding to each environmental control device within the detection area. This adjustment information includes specific adjustment amounts and adjustment actions, such as starting the humidifier and controlling the relative humidity (RH) of the humidifier to 58%RH.

[0068] Furthermore, after determining the adjustment information corresponding to each environmental control device within the detection area, the controller sends a corresponding first control command to each environmental control device. This first control command contains the adjustment information corresponding to the environmental control device, so that after receiving the first control command sent by the controller, each environmental control device performs corresponding operations according to the adjustment information contained in the first control command, adjusting the production environment of the detection area to the target state.

[0069] S203. Obtain the actual assembly image of at least one key assembly point in the assembly process corresponding to each detection area, and perform image detection on the actual assembly image of at least one key assembly point in the assembly process corresponding to each detection area to generate assembly quality detection results.

[0070] Optionally, critical assembly points refer to key locations in the assembly process corresponding to each inspection area that have a significant impact on the assembly quality of the electricity meter. During the execution of the assembly process corresponding to each inspection area, image acquisition devices set at each critical assembly point in each inspection area will acquire actual assembly images at each critical assembly point and send these images to the controller. The controller has pre-stored standard assembly images of each critical assembly point. After receiving the actual assembly images of each critical assembly point sent by the image acquisition devices in each inspection area, the controller performs image detection on the actual assembly images based on the standard assembly images of each critical assembly point to obtain the assembly result corresponding to the critical assembly point. Based on the assembly results of each critical assembly point, the assembly quality inspection result of the electricity meter is obtained. This assembly quality inspection result is used to indicate whether the electricity meter has assembly defects caused by changes in environmental parameters.

[0071] S204. Based on the assembly quality inspection results, determine at least one target adjustment parameter item, and adjust the value of the target adjustment parameter item by sending a second control command to the environmental control equipment corresponding to each target adjustment parameter item.

[0072] Optionally, the assembly quality inspection results, in addition to indicating whether the energy meter has assembly defects, also include the specific type of assembly defect and its location if defects are found. After determining the assembly quality inspection results of the energy meter, the controller can further optimize based on these results. That is, when assembly defects are found, the controller not only knows that the occurrence of the defects is related to environmental parameters, but also further analyzes which environmental parameter corresponding to which inspection area caused the defects, determining at least one target adjustment parameter item. Each target adjustment parameter item corresponds to an environmental control device, and the controller then sends a second control command to the corresponding environmental control device to adjust the value of the target adjustment parameter item.

[0073] Based on this, the electricity meter assembly quality inspection method according to the embodiments of this application, on the one hand, the controller quickly generates and issues a first control command based on real-time environmental parameters and environmental context information, realizing single active adjustment of environmental control equipment in each detection area, significantly improving the response speed of environmental parameter acquisition equipment and the control accuracy of environmental control equipment, reducing assembly risks caused by deviations in temperature, humidity, and air pressure from the source. On the other hand, by continuously acquiring actual assembly images in key processes and performing image detection that can be executed multiple times, dynamic and high-precision monitoring of assembly quality is formed, and the detection results are used as feedback signals to generate a second control command, dynamically optimizing the environmental parameter setpoints, and realizing quality-driven closed-loop adaptive control. This dual mechanism of active adjustment and continuous quality inspection feedback not only ensures the immediacy of environmental control, but also suppresses the generation of assembly defects through repeated iterative optimization, while using visual data to support objective quality judgment, overcoming the shortcomings of traditional methods that rely on human experience, have slow response, and are difficult to trace, and comprehensively improving the stability and intelligence level of electricity meter assembly.

[0074] As one possible implementation, step S202 above determines the adjustment information corresponding to each environmental control device within the detection area based on the environmental parameters collected by each environmental parameter acquisition device within the detection area and the environmental context information, including:

[0075] Based on the environmental parameters collected by each environmental parameter acquisition device within the testing area, external environmental information, the response characteristics of each environmental parameter acquisition device, the control logic rules of the assembly process corresponding to the testing area, and the preset energy consumption strategy, the adjustment information corresponding to each environmental control device within the testing area is determined.

[0076] Optionally, the environmental context information includes: external environmental information, response characteristics of each environmental parameter acquisition device, control logic rules for the assembly process corresponding to the detection area, and preset energy consumption strategies. External environmental information refers to the meteorological conditions outside the electricity meter's production area, such as outdoor temperature, humidity, and air pressure. The response characteristics of the environmental parameter acquisition devices refer to their dynamic performance, such as the different response delay times at different operating power levels. The control logic rules for the assembly process corresponding to the detection area refer to the process constraints that the assembly process must meet, such as maintaining a constant temperature of 23°C for ten minutes. The preset energy consumption strategy refers to the energy-saving targets for equipment operation, such as avoiding full-power operation of the environmental parameter acquisition devices and environmental control devices during periods of higher electricity prices.

[0077] Figure 3 A flowchart illustrating a method for determining adjustment information according to an embodiment of this application is shown. (Refer to...) Figure 3As shown, the above steps determine the adjustment information corresponding to each environmental control device in the detection area based on the environmental parameters collected by each environmental parameter acquisition device in the detection area, external environmental information, the response characteristics of each environmental parameter acquisition device, the control logic rules of the assembly process corresponding to the detection area, and the preset energy consumption strategy. Specifically, the steps include the following:

[0078] S301. Based on external environmental information, the response characteristics of each environmental parameter acquisition device, the control logic rules of the assembly process corresponding to the detection area, and the preset energy consumption strategy, determine the target environmental parameters of the detection area.

[0079] Optionally, since the external environment affects the efficiency and energy consumption of environmental control equipment, the response characteristics of environmental parameter acquisition equipment affect the timeliness and accuracy of environmental parameter acquisition, the control logic rules of the assembly process are a rigid requirement for environmental control in the assembly process, and the preset energy consumption strategy is a solution for energy efficiency optimization under the premise of meeting process requirements, the above factors will more or less affect the adjustment information of environmental control equipment. Therefore, in determining the adjustment information corresponding to environmental control equipment, this application takes into account process compliance, environmental adaptability, equipment capacity, and energy efficiency optimization, which makes the final determined target environmental parameters more reasonable and more suitable for the production environment of the testing area.

[0080] Optionally, external environmental information, the response characteristics of each environmental parameter acquisition device, the control logic rules of the assembly process corresponding to the detection area, and the preset energy consumption strategy are input into the pre-trained environmental decision model. Based on the control logic rules of the assembly process corresponding to the detection area, the environmental decision model determines the theoretical value and tolerance range of the environmental parameters. Based on the external environmental information, the response characteristics of each environmental parameter acquisition device, the preset energy consumption strategy, and the tolerance range, the theoretical value of the environmental parameters is adjusted to obtain the target environmental parameters.

[0081] For example, an environmental decision model is deployed on the controller. This model can employ a rule engine, machine learning model, or reinforcement learning model. The environmental decision model is pre-trained using production data containing multi-source information such as environmental parameters, energy consumption, and quality defects. Its training objective is to output target environmental parameters while meeting process requirements and minimizing energy consumption, thereby improving the stability of the production environment and reducing the incidence of assembly quality defects. The target environmental parameters refer to the environmental state that should be achieved within the detection area under the current production environment to meet the process requirements of the assembly process and energy-saving operation strategies, such as target temperature, target humidity, and target air pressure.

[0082] For example, external environmental information, the response characteristics of various environmental parameter acquisition devices, the control logic rules of the assembly process corresponding to the detection area, and a preset energy consumption strategy are used as inputs to the environmental decision model. After inputting these into the environmental decision model, the model extracts the standard process requirements for the assembly process based on the control logic rules, and determines the theoretical values ​​and tolerance ranges of the environmental parameters based on these requirements. The theoretical values ​​of the environmental parameters are the ideal environmental parameters specified by the assembly process, and the tolerance range is the allowable fluctuation range of the parameters.

[0083] Furthermore, based on the theoretical values ​​of environmental parameters, practical factors such as external environmental information, the response characteristics of each environmental parameter acquisition device, and preset energy consumption strategies are introduced. These factors are then combined with tolerance ranges to optimize and adjust the theoretical values ​​of environmental parameters, ultimately yielding the target environmental parameters. Specifically, the external environment is introduced to determine the feasibility of the adjustment operation. For example, if the outdoor temperature is extremely high, such as 40℃, lowering the temperature in the detection area, such as forcibly adjusting it to 20℃, would cause the air conditioning equipment to operate at high load. Clearly, adjusting the air conditioning temperature to 20℃ is not feasible in this situation. Introducing the response characteristics of the environmental parameter acquisition devices is to adjust the control margin. For example, if the temperature and humidity acquisition devices respond slowly, such as with a 10-second response delay, the collected environmental parameters will be inaccurate, potentially leading to overshooting issues in the corresponding air conditioning and humidification equipment. Introducing preset energy consumption strategies is to optimize equipment operating costs. For example, if the current period is peak electricity consumption, adjusting the operating parameters of the environmental control equipment by too large a range will increase the operating power of the environmental control equipment, thereby increasing operating costs. In this way, based on the theoretical values ​​of environmental parameters, the environmental decision-making model optimizes and corrects the theoretical values ​​of environmental parameters by taking into account real-world factors, and obtains target environmental parameters that enable more precise control over the production environment of the monitoring area.

[0084] S302. Based on the environmental parameters collected by each environmental parameter acquisition device and the target environmental parameters of the detection area, determine the environmental parameter change information of each environmental parameter acquisition device.

[0085] For example, the environmental parameter change information includes: deviation and trend. The deviation refers to the interpolation between the actual value and the target value of the environmental parameter, reflecting the degree to which the environmental parameters of the current production environment in the monitored area deviate from the target. The trend refers to the direction and rate of change of the environmental parameter over a period of time, reflecting whether the production environment is stabilizing.

[0086] For example, the environmental parameters collected by each environmental parameter acquisition device include the actual humidity collected by the humidity acquisition device, the actual temperature collected by the temperature acquisition device, and the actual air pressure value collected by the air pressure detection device. The target environmental parameters include the target temperature, target humidity, and target air pressure value. The deviation can be determined by calculating the difference between the actual humidity and the target humidity, the difference between the actual temperature and the target temperature, and the difference between the actual air pressure value and the target air pressure value.

[0087] For example, the trend can be determined based on time series analysis methods, such as linear regression and the difference method. Specifically, environmental parameters corresponding to multiple past time points can be fitted to obtain a trend curve. The trend can then be analyzed to determine the changing trend, which includes upward, downward, stable, and oscillating trends. An upward trend indicates a continuous increase in parameter values, such as a rising temperature; a downward trend indicates a continuous decrease in parameter values, such as a falling humidity; a stable trend indicates that the parameter values ​​fluctuate little and remain stable at a target value; and an oscillating trend indicates that the parameter values ​​fluctuate within a preset range of the target value.

[0088] In addition, by obtaining weather forecasts for a future time period and analyzing trends in humidity and temperature, early warning information can be generated based on these trends. This information can then be displayed to users through the front-end user interface provided by the controller. Specifically, the warning information can be displayed in the management account of the person in charge of the electricity meter's production area. Examples of warning information include: the rainy season is approaching, reminding users to pay attention to dehumidification; or: sudden weather changes or seasonal shifts such as high temperatures or winter cooling, reminding users to pay attention to the temperature of the production environment.

[0089] S303. Based on the response characteristics of each environmental parameter acquisition device and the environmental parameter change information, determine the corresponding adjustment information for each environmental control device.

[0090] Optionally, environmental parameter change information is a quantitative description of the current environmental state of the detection area, while the response characteristics of each environmental parameter acquisition device represent the device's dynamic performance, affecting the device's perception delay and measurement accuracy in relation to the real production environment. Based on the known response characteristics of each environmental parameter acquisition device and the environmental parameter change information, the controller determines the corresponding adjustment information for each environmental control device, such as how the environmental control device should operate. For example, it might activate the air conditioning system, lowering the air outlet temperature to 22°C, or turn on the humidifier and control the humidity to 58%RH. This avoids situations where the controller's control is untimely or overshoots due to lag in the environmental parameter acquisition equipment.

[0091] Accordingly, each environmental control device adjusts the production environment of the detection area according to the adjustment information contained in the first control command, including: if the humidity in the detection area is lower than the preset humidity range, controlling the humidifier to start humidifying to the target humidity; conversely, if the humidity in the detection area is higher than the preset humidity range, controlling the humidifier to remain off and the air conditioner vents to start dehumidification mode. If the temperature in the detection area is higher than the preset temperature range, controlling the air conditioner vents to start and adjusting the blowing temperature to the lowest temperature within the preset temperature range; conversely, if the temperature in the detection area is lower than the preset temperature range, controlling the air conditioner vents to start and adjusting the blowing temperature to the highest temperature within the preset temperature range. If the air pressure in the detection area is lower than the preset air pressure range, controlling the air compressor to increase the air pressure to the target air pressure value.

[0092] For example, each electricity meter is equipped with a QR code. During assembly, operators can scan the code to record the humidity, temperature, and air pressure of the meter during assembly, thus recording the environmental parameters during the assembly process. After the current meter is assembled, the operator can manually scan the QR code of the next meter. Based on this, the system further determines whether each meter has assembly defects and records the temperature, humidity, and air pressure corresponding to meters with defects, as well as those without defects, as sample data. Based on this sample data and a large model, learning analysis is performed to obtain the aforementioned preset ranges for humidity, temperature, and air pressure.

[0093] For example, regarding humidity control, when the humidity in the detection area is below a preset range, the humidifier is activated to increase the moisture content in the air. When the humidity is above the preset range, the humidifier is turned off, and the air conditioner vents are activated to enter dehumidification mode to reduce the water vapor content in the air and prevent condensation or moisture absorption by components. Regarding temperature control, if the temperature is above a preset temperature range, the air conditioner vents will automatically activate and set the outlet air temperature to the lowest value within that preset range for rapid cooling. Conversely, if the temperature is below the preset temperature range, the air conditioner will activate and blow out warm air at the highest temperature within that preset range to gradually increase the ambient temperature and prevent thermal shock or material shrinkage. Regarding air pressure control, if the air pressure is below a preset air pressure range, the system will activate or adjust the air compressor to increase the air supply and raise the area air pressure to the target value, ensuring the area maintains a positive pressure state and preventing external pollutants from entering.

[0094] In addition, if any of the environmental parameters—humidity, temperature, or air pressure—exceeds the corresponding risk threshold, the broadcast system in the production area (i.e., the production workshop) will announce a production halt. The system can also control the operation of humidification equipment, air conditioning equipment, and air compressors based on staff get off work hours and holiday schedules.

[0095] Based on this, a series of control operations on various environmental control devices by the controller realizes closed-loop and adaptive control of the production environment in the detection area, ensuring the stability, consistency and high quality of the electricity meter assembly process.

[0096] Figure 4 A flowchart illustrating a method for generating assembly quality inspection results according to an embodiment of this application is shown. (Refer to...) Figure 4 As shown, step S203 above performs image detection on the actual assembly image of at least one key assembly point in the assembly process corresponding to each detection area, and generates assembly quality inspection results. Specifically, it includes the following steps:

[0097] S401. For each inspection area, obtain standard assembly images of each key assembly point within the inspection area, as well as the annotation information of the standard assembly images.

[0098] The annotation information includes the first key feature area and the allowable error range. Standard assembly images can be obtained from energy meters that have been determined to be of high quality and without defects, or they can be generated using CAD tools for rendering and modeling or 3D rendering technology.

[0099] For example, for each detection area, the controller acquires standard assembly images of key assembly points in the corresponding assembly process. These standard assembly images represent the correct assembly result under ideal conditions, and are annotated with information including first key feature areas such as solder joint outlines, component edges, and pin alignment areas, as well as allowable error ranges such as component offset ≤0.1mm and solder joint area deviation ≤5%. This annotation information can be generated by an automated annotation tool, serving as a reference for subsequent image comparison to ensure that the detection has quantifiable judgment standards.

[0100] S402. For each key assembly point, align the actual assembly image of the key assembly point with the standard assembly image to obtain the processed assembly image. Based on the annotation information of the standard assembly image, perform image detection on the processed assembly image to generate the detection results of the key assembly points.

[0101] Optionally, for each key assembly point, the controller aligns the acquired actual assembly image with the standard assembly image using image registration techniques, such as affine transformation or perspective transformation based on feature point matching, to eliminate geometric deviations caused by differences in camera angle, position, or scaling. This ensures that the actual assembly image and the standard assembly image are precisely aligned in space, resulting in the processed assembly image, i.e., the aligned actual assembly image. Subsequently, based on the first key feature region and allowable error range marked in the standard assembly image, the controller performs local comparative analysis on the aligned actual assembly image. For example, by calculating the pixel differences, shape similarity, edge offset, or grayscale distribution changes of the key feature region, it determines whether the actual assembly deviates from the standard, thereby generating the detection result for that key assembly point. This detection result includes information such as the presence of defects, defect type, and confidence level.

[0102] Optionally, based on the first key feature region of the standard assembly image, the second key feature region of the processed assembly image is determined, and the difference between the first key feature region and the second key feature region is detected to obtain the initial difference detection result. Based on the initial difference detection result and the allowable error range, the detection result of the key assembly point is generated.

[0103] For example, the controller uses the first key feature region marked in the standard assembly image as a reference, and maps the first key feature region to the corresponding position in the aligned actual assembly image through the spatial transformation relationship after image registration, thereby determining the second key feature region to ensure that subsequent comparisons are performed at the same physical location and scale. Further, the controller performs pixel-level or feature-level difference analysis on the aligned first and second key feature regions, such as calculating structural similarity, edge deviation, grayscale difference, or geometric deformation, to generate initial difference detection results, quantifying the inconsistency between the actual assembly and the standard assembly.

[0104] Furthermore, the initial difference detection results are judged based on the allowable error range. If the difference is within the allowable error range, such as a part offset of 0.08mm, which is less than the allowable 0.1mm, the key assembly point is judged to be normal. If it exceeds the tolerance, such as a weld area reduction of 15%, which exceeds the allowable 10%, it is judged to have an assembly defect, and the defect type is marked. Finally, the detection result for the key assembly point is generated. In this way, by focusing on key feature areas, the risk of misjudgment from full-image comparison is avoided, and the accuracy and robustness of the detection are improved.

[0105] S403. Based on the inspection results of each key assembly point in each inspection area, generate assembly quality inspection results.

[0106] For example, the controller aggregates the inspection results of all critical assembly points within each inspection area and performs a fusion analysis. For instance, if any critical assembly point is determined to have a serious defect, the overall assembly quality inspection result is marked as unqualified; if there are slight deviations but all are within the allowable error range, it is judged as qualified. For multi-point defects, a weighted scoring mechanism can be introduced to comprehensively evaluate the overall quality and generate the final assembly quality inspection result.

[0107] In addition, the controller can generate a structured assembly quality inspection report based on the defect location, defect type and corresponding defect image, and display the assembly quality inspection report to the operator through the front-end user interface.

[0108] Based on this, by constructing a comparison system based on standard assembly images, and combining precise alignment and difference analysis of key feature areas, it is possible to effectively identify whether there are assembly defects at key assembly points, and to make quantitative judgments based on the allowable error range, thereby generating objective assembly quality inspection results. This not only improves the efficiency of quality inspection and avoids human error, but also provides reliable quality feedback data for subsequent environmental control and process optimization, realizing high-precision and automated visual inspection of the assembly quality of electricity meters.

[0109] As one possible implementation, step S204 above determines at least one target adjustment parameter item based on the assembly quality inspection result, including: if the assembly quality inspection result indicates that the energy meter has an assembly defect, then determine the target detection area that has the assembly defect, obtain the historical assembly environment parameters of the target detection area, and determine at least one target adjustment parameter item from the mapping relationship table based on the historical assembly environment parameters of the target detection area.

[0110] Optionally, when assembly defects are found in the energy meter during assembly quality inspection, a predefined mapping table can be used to quickly locate and identify environmental parameters that may cause the corresponding defects, thereby determining at least one target adjustment parameter that needs to be adjusted. The mapping table indicates the correlation between various assembly defects and environmental parameters affecting the assembly. For example, the mapping table is shown in Table 1 below. The assembly defect type refers to the specific defect type of the energy meter indicated by the assembly quality inspection results, such as cold solder joints, component drift, solder joint bridging, and poor sealing. Related environmental parameters refer to environmental variables that may affect the occurrence of assembly defects. For example, for the assembly defect of cold solder joints, moisture can cause solder paste oxidation, so the occurrence of cold solder joints is related to humidity. For the assembly defect of component drift, airflow can affect the surface mount, and the speed of airflow affects the air pressure, so the occurrence of component drift is related to air pressure. For the assembly defect of solder joint bridging, excessively rapid heating may cause abnormal solder flow, i.e., an excessively rapid temperature rise rate can affect solder joint welding, so the occurrence of solder joint bridging is related to temperature. Regarding the assembly defect of poor sealing, excessively low ambient temperatures may affect the curing of some sealing materials, thus the occurrence of poor sealing is temperature-related. Correlation refers to the direction and strength of the relationship between two variables: the type of assembly defect and relevant environmental parameters. It can be divided into positive and negative correlations. A positive correlation means that when the value of one variable increases, the value of the other variable tends to increase as well. For example, higher humidity increases the probability of the assembly defect of poor soldering. Conversely, a negative correlation means that when the value of one variable increases, the value of the other variable tends to decrease as well. For example, higher temperature shortens the curing time of the sealing material, and the lower the probability of the assembly defect of poor sealing.

[0111] Table 1 Mapping Relationship Table

[0112]

[0113] Optionally, if the assembly quality inspection result indicates that the energy meter has an assembly defect, the assembly quality inspection result also includes the specific type of assembly defect and the location information of the assembly defect. Then, based on the type and location information of the assembly defect, it can be determined which inspection area the assembly defect occurred in, and the corresponding inspection area can be used as the target inspection area, and the assembly process corresponding to the target inspection area can be determined.

[0114] Furthermore, during the assembly of the electricity meter, the assembly environment parameters and assembly time information corresponding to each detection area are stored in the database. After determining the target detection area where the assembly defect occurred, the historical assembly environment parameters of the target detection area are extracted from the data. These historical assembly environment parameters include environmental parameters such as temperature, humidity, and air pressure during a period of time before and after the assembly defect occurred. This period of time is, for example, a few minutes before and after the assembly defect occurred, and can be determined based on factors such as process characteristics and the sampling frequency of the environmental parameter acquisition equipment. Based on this, at least one target adjustment parameter item is determined from the mapping relationship table shown in Table 1, according to the historical assembly environment parameters of the target detection area. For example, based on the assembly defect type of the occurred assembly defect, the row corresponding to the assembly defect type is found in the mapping relationship table shown in Table 1, and the corresponding relevant environmental parameters and correlations are obtained. Combined with historical assembly environment parameters, it is determined which environmental parameters exceed the normal range and have a clear correlation with the assembly defect type, thereby determining one or more target adjustment parameter items that need to be adjusted. These target adjustment parameter items are specific environmental parameters.

[0115] Based on this, by combining assembly quality inspection results with environmental parameter control, and using a mapping table to establish the correlation between assembly defects and environmental factors, closed-loop quality control was achieved, thereby enabling precise and efficient adjustment of environmental parameters and improving assembly quality and the stability of electricity meter production.

[0116] Figure 5 A flowchart illustrating a parameter optimization method provided in an embodiment of this application is shown. (Refer to...) Figure 5 As shown, the method also includes:

[0117] S501. Obtain the sample dataset.

[0118] For example, the sample dataset includes first assembly environment parameters of multiple defect-free energy meters and second assembly environment parameters of multiple defective energy meters.

[0119] For example, a large number of assembly environment parameter records of electricity meters are collected from historical production data, and classified according to the final quality inspection results. The environmental parameters corresponding to electricity meters with qualified assembly quality and no defects are marked as the first assembly environment parameters, forming a positive sample, and the environmental parameters corresponding to electricity meters with assembly defects are marked as the second assembly environment parameters, forming a negative sample.

[0120] S502. Input the sample dataset into the pre-trained prediction model, determine multiple combinations of first parameters based on the sample dataset, iterate through each combination of first parameters, and determine the defect probability of the first parameter combination for the currently iterated first parameter combination.

[0121] For example, after obtaining the sample dataset, it is input into a pre-trained prediction model. The prediction model can learn the non-linear relationship between environmental parameters and defect occurrence. This prediction model can be, for example, a classification model or a regression model. The classification model focuses on predicting whether assembly defects are likely to occur under a certain combination of environmental parameters, while the regression model focuses on predicting the assembly quality rate under a certain combination of environmental parameters. After obtaining the input, the prediction model extracts multiple first parameter combinations that may affect assembly quality from the sample dataset. These first parameter combinations are, for example, humidity 65% ​​+ temperature 24°C + air pressure 1012hPa. Then, it iterates through each first parameter combination, using the weights and probability functions inside the prediction model to calculate the defect probability of assembly defects in the electricity meter under each first parameter combination. This enables the ability to mine key environmental risk factors from historical data and identify which combination of environmental parameters is more likely to cause assembly quality problems.

[0122] S503. Based on the defect probability of each first parameter combination, determine the range of optimization parameters, and determine multiple second parameter combinations within the range of optimization parameters and the energy consumption information corresponding to each second parameter combination.

[0123] For example, based on the defect probability of each first parameter combination, an optimized parameter range is determined. This optimized parameter range is, for example, an environmental parameter range where the defect probability is below a preset threshold, such as 5%. Operating within this optimized parameter range can significantly reduce the risk of assembly defects. Further, multiple second parameter combinations are determined within this optimized parameter range. These second parameter combinations are feasible environmental parameter configurations to further meet quality requirements. Combining equipment energy consumption and measured data, the energy consumption information corresponding to each second parameter combination is determined, such as the power consumption of air conditioning equipment and the power consumption of humidification equipment.

[0124] S504. Based on the energy consumption information corresponding to each combination of second parameters, select the target parameter combination from multiple combinations of second parameters.

[0125] For example, after obtaining multiple combinations of second parameters that meet quality requirements and have clear energy consumption information, the target parameter combination with the best overall performance is selected from the multiple combinations of second parameters. For example, the set of second parameter combinations with the lowest energy consumption under the premise of ensuring the lowest defect probability is selected as the target parameter combination. This target parameter combination is the recommended best environmental control strategy, which can be used to guide the operation of environmental control equipment in actual production assembly and achieve synergistic optimization of high quality and low energy consumption.

[0126] Based on this, and using historical assembly data and predictive models, the system automatically identifies high-risk combinations of environmental parameters that lead to assembly defects, and then reverse-engineers the target combination of environmental parameters that ensures both assembly quality and optimal energy consumption. This not only improves the yield rate and stability of the electricity meter assembly process, but also reduces production costs through refined energy consumption management.

[0127] This application also provides a controller 600, such as... Figure 6 The diagram shown is a structural schematic of the controller 600 provided in an embodiment of this application, including: a processor 601 and a memory 602, and optionally, a bus 603. The memory 602 stores machine-readable instructions executable by the processor 601. When the controller 600 is running, the processor 601 and the memory 602 communicate via the bus 603. When the machine-readable instructions are executed by the processor 601, the steps in the energy meter assembly quality inspection method described in any of the preceding claims are performed.

[0128] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the electricity meter assembly quality inspection method as described in any of the preceding claims.

[0129] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some communication interfaces; the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0130] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0131] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for detecting assembly quality of an electric energy meter, characterized in that, The controller is applied to an environment control system in an electric energy meter production environment, and the system comprises the controller, a plurality of environment regulation devices arranged in each detection area, and environment parameter acquisition devices corresponding to each environment regulation device. The detection area is determined according to the assembly process information of the electric energy meter. The method comprises the following steps: acquiring environment parameters collected by each environment parameter acquisition device in each detection area; for each detection area, determining adjustment information corresponding to each environment regulation device in the detection area according to the environment parameters collected by each environment parameter acquisition device in the detection area and environment context information, and sending corresponding first control instructions to each environment regulation device, so that each environment regulation device adjusts the production environment of the detection area according to the adjustment information contained in the first control instruction; acquiring actual assembly images of at least one key assembly point in the assembly process corresponding to each detection area, and performing image detection on the actual assembly images of at least one key assembly point in the assembly process corresponding to each detection area to generate assembly quality detection results, which are used to indicate whether the electric energy meter is defective due to changes in environment parameters; determining at least one target adjustment parameter item according to the assembly quality detection results, and adjusting the value of the target adjustment parameter item by sending a second control instruction to the environment regulation device corresponding to the target adjustment parameter item; the image detection on the actual assembly images of at least one key assembly point in the assembly process corresponding to each detection area to generate assembly quality detection results comprises the following steps: for each detection area, acquiring standard assembly images of each key assembly point in the detection area and annotation information of the standard assembly images, wherein the annotation information comprises a first key feature area and an allowable error range; for each key assembly point, aligning the actual assembly image of the key assembly point with the standard assembly image to obtain a processed assembly image, and performing image detection on the processed assembly image based on the annotation information of the standard assembly image to generate a detection result of the key assembly point; generating the assembly quality detection results according to the detection results of each key assembly point in each detection area; the image detection on the processed assembly image based on the annotation information of the standard assembly image to obtain the detection result of the key assembly point comprises the following steps: determining a second key feature area of the processed assembly image according to the first key feature area of the standard assembly image; performing difference detection on the first key feature area and the second key feature area to obtain an initial difference detection result, and generating the detection result of the key assembly point according to the initial difference detection result and the allowable error range.

2. The method of claim 1, wherein, the determination of the adjustment information corresponding to each environment regulation device in the detection area according to the environment parameters collected by each environment parameter acquisition device in the detection area and the environment context information comprises the following steps: According to the environmental parameters collected by the environmental parameter collection devices, the external environment information, the response characteristics of the environmental parameter collection devices, the control logic rules of the assembly process corresponding to the detection area, and the preset energy consumption strategy, the adjustment information corresponding to the environmental regulation devices in the detection area is determined.

3. The method of claim 2, wherein, According to the environmental parameters collected by the environmental parameter collection devices, the external environment information, the response characteristics of the environmental parameter collection devices, the control logic rules of the assembly process corresponding to the detection area, and the preset energy consumption strategy, the adjustment information corresponding to the environmental regulation devices in the detection area is determined. According to the external environment information, the response characteristics of the environmental parameter collection devices, the control logic rules of the assembly process corresponding to the detection area, and the preset energy consumption strategy, the target environmental parameters of the detection area are determined. According to the environmental parameters collected by the environmental parameter collection devices and the target environmental parameters of the detection area, the environmental parameter change information of each environmental parameter collection device is determined, and the environmental parameter change information includes a deviation and a change trend. According to the response characteristics of the environmental parameter collection devices and the environmental parameter change information, the adjustment information corresponding to the environmental regulation devices is determined.

4. The method of claim 3, wherein, According to the external environment information, the response characteristics of the environmental parameter collection devices, the control logic rules of the assembly process corresponding to the detection area, and the preset energy consumption strategy, the target environmental parameters of the detection area are determined. The external environment information, the response characteristics of the environmental parameter collection devices, the control logic rules of the assembly process corresponding to the detection area, and the preset energy consumption strategy are input into a pre-trained environmental decision model, and the environmental decision model determines an environmental parameter theoretical value and a tolerance range based on the control logic rules of the assembly process corresponding to the detection area. The target environmental parameters are obtained by adjusting the environmental parameter theoretical value based on the external environment information, the response characteristics of the environmental parameter collection devices, the preset energy consumption strategy, and the tolerance range.

5. The method of claim 1, wherein, The detection area is determined according to the following steps: According to the assembly process flow of the electric energy meter, the production area of the electric energy meter is divided into multiple functional areas, and each functional area corresponds to an assembly process. According to the influence degree of each functional area on the assembly quality of the electric energy meter, the influence weight of each functional area is determined. The functional area with an influence weight greater than a preset value is regarded as the detection area.

6. The method of claim 1, wherein, According to the assembly quality detection result, at least one target adjustment parameter item is determined, including: If the assembly quality detection result indicates that the electric energy meter has assembly defects, the target detection area with assembly defects is determined, and the historical assembly environmental parameters of the target detection area are obtained. According to a historical assembly environment parameter of the target detection area, at least one target adjustment parameter item is determined from a mapping relationship table, wherein the mapping relationship table is used to indicate an association relationship between various assembly defects and environment parameters affecting assembly.

7. The method of claim 1, wherein, Also comprising: Obtaining a sample data set, wherein the sample data set comprises first assembly environment parameters of a plurality of flawless electric energy meters and second assembly environment parameters of a plurality of defective electric energy meters; Inputting the sample data set into a pre-trained prediction model, determining a plurality of first parameter combinations according to the sample data set, and traversing each first parameter combination, and determining a defect probability of the first parameter combination for the currently traversed first parameter combination; According to the defect probability of each first parameter combination, an optimization parameter range is determined, a plurality of second parameter combinations within the optimization parameter range are determined, and energy consumption information corresponding to each second parameter combination is determined; According to the energy consumption information corresponding to each second parameter combination, a target parameter combination is selected from the plurality of second parameter combinations.

8. An electric energy meter production environment control system characterized by comprising: Comprising: A controller, a plurality of environment control devices arranged in each detection area, and an environment parameter acquisition device corresponding to each environment control device; Each of the environment control devices and the environment parameter acquisition devices is connected to the controller; The controller is used to execute the steps in the electric energy meter assembly quality detection method of any one of claims 1-7.

Images