Compact shelving electrical control method and device and electronic equipment

Abstract

The invention provides a compact shelving electrical control method and device and electronic equipment, and relates to the field of data processing. In the method, first environment data of an environment where a target compact shelf is located at present is obtained, and the first environment data comprises temperature data, humidity data, illumination data and vibration data; predicting the environment where the target compact shelving is located within a preset time period by adopting a time sequence prediction algorithm to obtain second environment data; determining the working state of the target compact shelf by adopting a support vector machine algorithm according to the second environment data; and if it is determined that the working state indication is abnormal, generating a corresponding control strategy. By implementing the technical scheme provided by the invention, the electrical control efficiency of the compact shelving can be conveniently improved.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and in particular to a method, device and electronic equipment for controlling electrical components of a compact shelving system. Background Art

[0002] Compact shelving is widely used in major state-owned enterprises, shopping malls, schools, private enterprise data rooms, hospital sample rooms, etc. due to its large storage capacity, space saving, and convenient management. Especially in electrical cabinets, compact shelving can effectively utilize limited space to store a large number of electrical equipment or components, improving storage efficiency and space utilization.

[0003] At present, when the compact shelving in the electrical cabinet is electrically controlled, the detection part mainly relies on manual methods. This traditional method is not only time-consuming and labor-intensive, but also limited by the efficiency of manual operation, which often leads to the formulation of subsequent control strategies not being timely enough. Specifically, manual inspection requires checking the compact shelving in the electrical cabinet one by one and recording various parameters and states, such as load-bearing capacity, stability, and transmission system performance. In this process, human factors such as fatigue and misjudgment may have an adverse effect on the test results, greatly increasing the possibility of rework and repair of the manually formulated control strategy, thereby affecting the overall electrical control efficiency of the compact shelving.

[0004] Therefore, there is an urgent need for an electrical control method, device and electronic equipment for compact racks. Summary of the invention

[0005] The present application provides a method, device and electronic equipment for electrical control of a compact shelving system, which are convenient for improving the electrical control efficiency of the compact shelving system.

[0006] In a first aspect of the present application, a method for electrical control of a compact shelving is provided, the method comprising: obtaining first environmental data of a current environment of a target compact shelving, the first environmental data comprising temperature data, humidity data, light data and vibration data; using a time series prediction algorithm to predict the environment of the target compact shelving within a preset time period to obtain second environmental data; based on the second environmental data, using a support vector machine algorithm to determine a working state of the target compact shelving; if it is determined that the working state indicates an abnormality, generating a corresponding control strategy.

[0007] By adopting the above technical solution, the system can fully understand the environmental conditions of the target compact shelving by obtaining multi-dimensional environmental data such as temperature, humidity, light and vibration. These parameters are crucial for evaluating whether the storage environment of the compact shelving is suitable and preventing potential failures. The time series prediction algorithm is used to predict the environment within a preset time period, so that the system can respond before the environment changes. This prediction capability helps to detect possible environmental problems in a timely manner, so that measures can be taken in advance to avoid damage to the compact shelving and its stored items. According to the predicted environmental data, the support vector machine algorithm is used to determine the working status of the target compact shelving. This method not only improves the accuracy of judgment, but also can automatically adapt to the working status of the compact shelving under different environmental conditions, reducing the possibility of manual intervention and misjudgment. When the system determines that the working status of the compact shelving indicates an abnormality, it can quickly generate a corresponding control strategy. This rapid response mechanism helps to solve problems in a timely manner and prevent problems from further deteriorating, thereby ensuring the safety and stability of the compact shelving and its stored items. Through an automated and intelligent monitoring and prediction system, the cost and time of manual monitoring can be significantly reduced, and management efficiency can be improved. At the same time, the accuracy and reliability of the system are also higher, which can provide users with more accurate and reliable data support. By real-time monitoring and predicting environmental changes, the system can promptly detect and prevent potential risk factors. This preventive management strategy helps reduce the company's operating costs and risks. Therefore, it is convenient to improve the electrical control efficiency of the compact shelving.

[0008] Optionally, the acquiring of the first environmental data of the current environment of the target compact shelving specifically includes: receiving the original temperature data of the current environment of the target compact shelving sent by a temperature sensor; receiving the original humidity data of the current environment of the target compact shelving sent by a humidity sensor; receiving the original light data of the current environment of the target compact shelving sent by a light sensor; receiving the original vibration data of the current environment of the target compact shelving sent by a vibration sensor; and preprocessing the original temperature data, the original humidity data, the original light data and the original vibration data to obtain the first environmental data, wherein the preprocessing includes denoising, filtering and normalization.

[0009] By adopting the above technical solution, the directness and accuracy of the data are ensured by directly receiving the raw data from the temperature sensor, humidity sensor, light sensor and vibration sensor. The errors or loss that may occur in the data transmission or transfer process are avoided, thereby improving the reliability of subsequent analysis and prediction. Raw data often contains noise, interference or outliers, which will affect the subsequent data analysis and prediction results. Through denoising, filtering and normalization processing, these unfavorable factors can be effectively removed to improve the quality and consistency of the data. Denoising can eliminate random fluctuations or errors in the data, making the data smoother and more stable; filtering can retain useful information in the data while removing high-frequency noise or irrelevant information; normalization can scale the data to the same order of magnitude, which is convenient for subsequent data analysis and processing. The preprocessed data is more standardized and standardized, which is convenient for subsequent data analysis and processing. This can not only improve the efficiency of data processing, but also make the data easier to understand and use. The preprocessed data is also more suitable for training and prediction of machine learning algorithms, because the algorithm usually has certain requirements on the format and quality of the input data. By preprocessing the raw data, the robustness and stability of the entire monitoring system can be enhanced. Even if some abnormal situations or data quality problems are encountered in actual applications, the system can make certain compensations and corrections through the preprocessing process to maintain the reliability and accuracy of the data.

[0010] Optionally, the use of a time series prediction algorithm to predict the environment of the target compact shelving within a preset time period to obtain second environmental data specifically includes: inputting the first environmental data into a preset time series model to generate an environmental feature vector, the preset time series model is pre-constructed by the time series prediction algorithm; determining a time feature vector according to the preset time period; predicting the environmental feature vector and the time feature vector through the preset time series model to generate a pointing environment sequence; generating the second environmental data according to the pointing environment sequence.

[0011] By adopting the above technical solution, by inputting the first environmental data into a preset time series model and using the model to generate an environmental feature vector, key information and trends in the environmental data can be captured. This helps to more accurately predict future changes in environmental data, so that corresponding measures can be taken in advance. Determining the time feature vector is an important step in the prediction process. The time feature vector can reflect the time correlation and periodic changes in the time series data, which is crucial to improving the prediction accuracy. By combining the time feature vector with the environmental feature vector, the change law of the environmental data can be more comprehensively considered, thereby improving the accuracy and reliability of the prediction. The preset time period can be flexibly set according to actual needs, which helps to adapt to the prediction needs in different scenarios. The pointing environmental sequence generated by the preset time series model can clearly show the change trend of environmental data in the future time period. This highly interpretable prediction result helps users better understand the prediction results and formulate corresponding control strategies based on the prediction results. Accurate prediction results can provide strong support for decision-making. By understanding the change trend of future environmental data in advance, users can make decisions more quickly, thereby avoiding potential risks and losses. This helps to improve decision-making efficiency and response speed.

[0012] Optionally, the working status of the target compact shelving is determined based on the second environmental data using a support vector machine algorithm, specifically including: performing missing value processing on the second environmental data using a mean filling method to obtain a target feature group; calculating the target feature group using the support vector machine algorithm to obtain a feature space position; determining a positional relationship between the feature space position and a hyperplane corresponding to the support vector machine algorithm; and generating a monitoring result based on the positional relationship, wherein the monitoring result is used to indicate the working status of the target compact shelving.

[0013] By adopting the above technical solution, the missing value processing of the second environment data by the mean filling method can effectively solve the problem of missing data. This helps to ensure that the data input into the support vector machine algorithm is complete and accurate, thereby improving the calculation accuracy and reliability of the algorithm. The feature space position can be obtained by calculating the target feature group through the support vector machine algorithm. This process can map high-dimensional data into a low-dimensional feature space while retaining the key information and classification characteristics of the data. This helps to more accurately describe and identify the working state of the target compact rack. By judging the positional relationship between the feature space position and the hyperplane corresponding to the support vector machine algorithm, a quick judgment of the working state of the target compact rack can be achieved. The hyperplane obtained by training the support vector machine algorithm can divide the data points into different categories, thereby realizing the classification and identification of the working state of the target compact rack. The monitoring results generated according to the positional relationship can accurately indicate the working state of the target compact rack. This result not only has a clear indicative significance, but also can provide strong support for the subsequent control strategy formulation. At the same time, since the support vector machine algorithm has good generalization ability, the generated monitoring results also have good stability and reliability. Accurate monitoring results can help to promptly detect abnormal working conditions of the target compact shelving, so that maintenance and management measures can be taken in a timely manner. This can not only avoid potential safety risks and losses, but also improve the operating efficiency and life of the equipment.

[0014] Optionally, the method also includes: based on the position relationship, calculating a probability value, the probability value including a first probability value and a second probability value, the first probability value being used to represent the probability value corresponding to the feature space position on the first side of the hyperplane, and the second probability value being used to represent the probability value corresponding to the feature space position on the second side of the hyperplane, the first side and the second side being two opposite sides of the hyperplane; if it is determined that the feature space position is located on the first side, and the first probability value is greater than or equal to a preset threshold, then it is determined that the monitoring result indicates normal, and then it is determined that the working status of the target compact shelving indicates normal; if it is determined that the feature space position is located on the second side, and the second probability value is greater than or equal to the preset threshold, then it is determined that the monitoring result indicates abnormal, and then it is determined that the working status of the target compact shelving indicates abnormal.

[0015] By adopting the above technical solution, the working status of the target dense shelving can be evaluated more carefully by calculating the probability value of the feature space position on both sides of the hyperplane. This method not only takes into account the positional relationship, but also combines the information of probability statistics, thereby improving the accuracy and reliability of the judgment. The preset threshold is set as the judgment standard, making the generation of monitoring results clearer and easier to implement. When the feature space position is located on one side and the corresponding probability value is greater than or equal to the preset threshold, the monitoring result and working status can be directly determined, reducing the complexity and subjectivity of human judgment. This method has good adaptability, and the preset threshold can be adjusted according to the actual situation to meet the judgment needs in different scenarios. Through clear judgment criteria and probability value calculation, the monitoring results and working status can be quickly obtained, thereby improving decision-making efficiency. This is especially important for scenarios that require timely response and processing.

[0016] Optionally, if it is determined that the working status indicates an abnormality, a corresponding control strategy is generated, specifically including: if it is determined that the working status indicates a temperature abnormality, a corresponding temperature control strategy is generated; the temperature control strategy is sent to a fan device to control the fan device to cool down the target compact shelving according to the temperature control strategy.

[0017] By adopting the above technical solution, once it is determined that the working status of the target compact shelving indicates an abnormality, the system can quickly generate a corresponding control strategy. This immediate response helps to reduce potential losses that may be caused by equipment failure or environmental changes, and ensure the safety of equipment and stored items. According to different types of abnormalities, the system can generate targeted control strategies. This accuracy ensures the effectiveness of problem solving and avoids unnecessary resource consumption and erroneous operations. By sending control strategies to fan devices, automatic control of the target compact shelving is achieved. This automation not only improves the convenience of operation, but also reduces errors and delays in human operation, and improves the overall efficiency of the system. For potential risks such as temperature abnormalities, timely control strategies can prevent further problems from occurring. By timely and effective control of the target compact shelving, its optimal working state can be maintained, thereby extending the service life of the equipment and reducing the cost of maintenance and replacement. Automated and immediate control strategies reduce user intervention in equipment management and improve user experience. Users can focus more on other important tasks without worrying about the operating status of the equipment.

[0018] Optionally, the method also includes: determining training data based on the historical electrical control data of the target dense shelving; using a sliding window to extract the target time point in the training data, and the statistical features corresponding to the target time point, the statistical features including mean, standard deviation, maximum value, minimum value and time slope; generating the time series features according to the mean, the standard deviation, the maximum value, the minimum value and the time slope; using the time series features to train the initial model to obtain the correspondence between the time series features and labels, the labels including normal and abnormal; performing parameter optimization on the initial model, and through repeated iterations, obtaining the preset time series model that meets the preset standards or converges.

[0019] By adopting the above technical solution, by analyzing the historical electrical control data of the target compact shelving, the existing data resources can be fully utilized to provide rich samples for model training. This helps to improve the generalization ability and accuracy of the model. The sliding window technology is used to extract the target time point and its corresponding statistical features, which can more comprehensively capture the key information and trends in the data. These statistical features help to reveal the laws and patterns behind the data and provide strong support for model training. The extracted statistical features are integrated into time series features, so that the model can process time series data and capture the dynamic characteristics of data changing over time. This is crucial for predicting future data trends and anomaly detection. By training the model, the correspondence between time series features and labels can be established. This enables the model to accurately judge the working status of the target compact shelving based on the input time series features, providing decision support for subsequent monitoring and management. The parameters of the initial model are optimized, and through repeated iterations, a preset time series model that meets the preset standards or converges can be obtained. This process can continuously improve the performance of the model and ensure its accuracy and reliability in practical applications. Through the above steps, a time series prediction model with superior performance can be constructed. The model can accurately predict the future working status of the target compact shelving, detect potential problems in a timely manner, and adopt corresponding control strategies to reduce failure rate and maintenance costs.

[0020] In a second aspect of the present application, an electrical control device for a compact shelving system is provided, the electrical control device for the compact shelving system comprising an acquisition module and a processing module, wherein the acquisition module is used to acquire first environmental data of a current environment of a target compact shelving system, the first environmental data comprising temperature data, humidity data, light data and vibration data; the processing module is used to use a time series prediction algorithm to predict the environment of the target compact shelving system within a preset time period to obtain second environmental data; the processing module is also used to determine a working state of the target compact shelving system based on the second environmental data using a support vector machine algorithm; the processing module is also used to generate a corresponding control strategy if it is determined that the working state indicates an abnormality.

[0021] In the third aspect of the present application, an electronic device is provided, which includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs the method described above.

[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, the method described above is executed.

[0023] In summary, one or more technical solutions provided in this application have at least the following technical effects or advantages: By acquiring multi-dimensional environmental data such as temperature, humidity, light and vibration, the system can fully understand the environmental conditions of the target compact shelving. These parameters are crucial for evaluating whether the storage environment of the compact shelving is suitable and preventing potential failures. The time series prediction algorithm is used to predict the environment within a preset time period, allowing the system to respond before the environment changes. This prediction capability helps to detect possible environmental problems in a timely manner, so that measures can be taken in advance to avoid damage to the compact shelving and its stored items. Based on the predicted environmental data, the support vector machine algorithm is used to determine the working status of the target compact shelving. This method not only improves the accuracy of judgment, but also can automatically adapt to the working status of the compact shelving under different environmental conditions, reducing the possibility of manual intervention and misjudgment. When the system determines that the working status of the compact shelving indicates an abnormality, it can quickly generate a corresponding control strategy. This rapid response mechanism helps to solve problems in a timely manner and prevent problems from further deteriorating, thereby ensuring the safety and stability of the compact shelving and its stored items. Through an automated and intelligent monitoring and prediction system, the cost and time of manual monitoring can be significantly reduced, and management efficiency can be improved. At the same time, the accuracy and reliability of the system are also higher, which can provide users with more accurate and reliable data support. By real-time monitoring and predicting environmental changes, the system can promptly detect and prevent potential risk factors. This preventive management strategy helps reduce the company's operating costs and risks. Therefore, it is convenient to improve the electrical control efficiency of the compact shelving. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A flow chart of a method for electrical control of a compact shelving system provided in an embodiment of the present application.

[0025] Figure 2 Another flow chart of a compact shelving electrical control method provided in an embodiment of the present application.

[0026] Figure 3 A module schematic diagram of a compact shelving electrical control device provided in an embodiment of the present application.

[0027] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0028] Explanation of the reference numerals: 31, acquisition module; 32, processing module; 41, processor; 42, communication bus; 43, user interface; 44, network interface; 45, memory. DETAILED DESCRIPTION

[0029] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0030] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0031] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0032] As an efficient storage solution, compact shelving has won wide recognition and application in many fields such as state-owned enterprises, commercial shopping centers, educational institutions, archives of private enterprises and sample storage rooms of medical institutions due to its excellent storage capacity, space optimization characteristics and convenient management methods. Especially in the application scenario of electrical cabinets, compact shelving has shown its incomparable advantages. It can cleverly use every inch of precious space in the electrical cabinet and accommodate a large number of electrical equipment or components in an orderly manner, thereby greatly improving the storage efficiency and space utilization efficiency.

[0033] However, in the current electrical control system of electrical cabinet shelving, the detection link mainly relies on the traditional manual operation mode. This situation not only reflects the lag in technology iteration, but also reveals the limitations in efficiency and accuracy. Specifically, the manual inspection process requires staff to check the shelving in the electrical cabinet one by one, and record in detail various key parameters and operating conditions including load-bearing limit, structural stability, smoothness and efficiency of the transmission system. This cumbersome process not only consumes a lot of time and human resources, but is also easily interfered by human factors, such as physical fatigue, distraction or misjudgment of the inspector, which may become potential risk points that affect the accuracy of the test results.

[0034] Furthermore, the subsequent electrical control strategies formulated based on the data obtained from manual inspection may face frequent adjustments and optimization needs due to inaccurate or untimely collection of preliminary data, and may even cause unnecessary rework and maintenance operations, which undoubtedly increases management costs and reduces the response speed and control efficiency of the entire compact shelving electrical control system.

[0035] In order to solve the above technical problems, the present application provides a compact rack electrical control method, referring to Figure 1 , Figure 1 A flowchart of a compact rack electrical control method provided in an embodiment of the present application. The method is applied to a server and includes steps S110 to S140, which are as follows: S110, obtaining first environmental data of the current environment of the target compact shelving, where the first environmental data includes temperature data, humidity data, light data, and vibration data.

[0036] Specifically, a server refers to a computer system that processes data and provides services. It can be a physical server or a virtual machine or container running in the cloud. The target compact rack refers to a storage device whose specific environmental parameters need to be monitored. This device is used to store components in the electrical cabinet that are sensitive to environmental conditions, such as precision instruments, electronic products, etc. The current environment refers to the physical space where the target compact rack is currently located and the natural environment around its electrical cabinet. The first environmental data refers to a series of environmental parameter data obtained by the server from the current environment of the target compact rack. The temperature data refers to the temperature value of the environment where the target compact rack is located. This value is used to evaluate whether the environment is suitable for storing specific components. The humidity data refers to the humidity value of the environment where the target compact rack is located. Too high or too low humidity may cause damage to the stored components. The light data refers to the light intensity value of the environment where the target compact rack is located. For some components that are sensitive to light, this value is particularly important. The vibration data refers to the vibration of the environment where the target compact rack is located. The vibration may come from factors such as the operation of surrounding equipment and traffic, which may have an adverse effect on stored components such as precision instruments.

[0037] In a possible implementation, first environmental data of the current environment of the target compact shelving is obtained, specifically including: receiving original temperature data of the current environment of the target compact shelving sent by a temperature sensor; receiving original humidity data of the current environment of the target compact shelving sent by a humidity sensor; receiving original light data of the current environment of the target compact shelving sent by a light sensor; receiving original vibration data of the current environment of the target compact shelving sent by a vibration sensor; and preprocessing the original temperature data, original humidity data, original light data, and original vibration data to obtain first environmental data, wherein the preprocessing includes denoising, filtering, and normalization.

[0038] Specifically, the server receives data from a temperature sensor installed near the target compact rack through a communication method, such as wired or wireless. These data are raw, unprocessed temperature values, reflecting the temperature of the target compact rack's current environment. Similarly, the server also receives raw humidity data from the humidity sensor. These data reflect the humidity of the target compact rack's environment. The server also receives raw light data from the light sensor. These data represent the light intensity of the target compact rack's environment. Finally, the server receives raw vibration data from the vibration sensor. These data reflect the vibration of the target compact rack's environment, which may come from other devices in the electrical cabinet or external factors. After receiving these raw data, the server performs a series of preprocessing operations, including removing noise or outliers from the data; smoothing the data to remove high-frequency fluctuations; and scaling the data to a specific range for subsequent analysis or comparison. The purpose of these preprocessing steps is to improve the accuracy and reliability of the data and provide support for subsequent analysis and decision-making.

[0039] S120, using a time series prediction algorithm to predict the environment of the target compact shelving within a preset time period to obtain second environment data.

[0040] Specifically, time series prediction algorithms are a type of algorithm specifically used to predict data values ​​at future time points. They predict future data changes by analyzing factors such as time trends and periodic changes in historical data. The server will use the time series prediction algorithm to predict the environment of the target compact cabinet in a preset time period in the future, such as the next 24 hours, the next week, etc. The prediction content includes environmental parameters such as temperature, humidity, light intensity, and vibration. After the prediction algorithm runs, the server will output the prediction results, that is, the environmental data of the target compact cabinet in the preset time period in the future. These data are called second environmental data. They are estimates of future environmental conditions and can be used to formulate countermeasures or issue early warnings. Among them, the preset time period is customized by the manager of the target compact cabinet.

[0041] In one possible implementation, a time series prediction algorithm is used to predict the environment of a target compact shelving unit within a preset time period to obtain second environment data, specifically including: inputting the first environment data into a preset time series model to generate an environment feature vector, the preset time series model is pre-constructed by a time series prediction algorithm; determining a time feature vector according to a preset time period; predicting the environment feature vector and the time feature vector through the preset time series model to generate a pointing environment sequence; generating second environment data according to the pointing environment sequence.

[0042] Specifically, the server inputs the first environmental data into a preset time series model, and the model analyzes the data and generates an environmental feature vector. This vector contains information extracted from the data that can represent environmental features. The preset time series model is pre-constructed by a time series prediction algorithm and is used to predict future environments. In an embodiment of the present application, the time series prediction algorithm preferably uses a long short-term memory network. The time feature vector is a set of time-related feature values ​​determined according to a preset time period, such as the position of a time point, the length of a time period, periodicity, etc. In this step, the server generates a time feature vector according to the preset time period for subsequent prediction processes. Next, the server inputs the environmental feature vector and the time feature vector into the preset time series model together. The model combines the two vectors and uses the time series prediction algorithm to predict and generate a pointing environment sequence. This sequence contains the predicted values ​​of environmental parameters at each time point in the future preset time period. The pointing environment sequence is a preliminary form of the prediction result, which contains the predicted values ​​of environmental parameters at each time point in the future preset time period. Among them, the server further processes and formats the pointing environment sequence to generate second environmental data. These data are presented in the form of time series, with each time point corresponding to a predicted value, and include all environmental parameters that need to be predicted, such as temperature, humidity, light, vibration, etc.

[0043] S130. Determine the working state of the target compact shelving system using a support vector machine algorithm according to the second environment data.

[0044] Specifically, a support vector machine is a supervised learning model for classification and regression analysis. It maps the input data to a high-dimensional feature space and finds an optimal hyperplane in the space to separate data points of different categories. In an embodiment of the present application, the server will use a support vector machine algorithm to analyze the second environmental data to determine the working status of the target compact shelving. The working status refers to the operating state or performance that the target compact shelving may be in within a preset time period in the future. By analyzing the second environmental data, the server can predict the working state of the target compact shelving under different environmental conditions, such as normal operation, overload, failure, etc.

[0045] In a possible implementation, a support vector machine algorithm is used to determine the working status of a target compact shelving system based on the second environmental data, specifically including: using a mean filling method to process missing values ​​in the second environmental data to obtain a target feature group; using a support vector machine algorithm to calculate the target feature group to obtain a feature space position; determining a positional relationship between the feature space position and a hyperplane corresponding to the support vector machine algorithm; and generating a monitoring result based on the positional relationship, wherein the monitoring result is used to indicate the working status of the target compact shelving system.

[0046] Specifically, in practical applications, the second environment data may have missing values ​​due to various reasons, such as sensor failure, data transmission problems, etc. The mean filling method is a missing value processing method that fills the missing values ​​with the average value of the feature where the missing value is located. The data processed by the mean filling method, that is, the target feature group, will be used for subsequent support vector machine algorithm calculations. In this process, the server will input the target feature group into the trained support vector machine model, and the model will calculate the position of the target feature group in the feature space. In the support vector machine algorithm, the optimal hyperplane is used to separate data points of different categories. The server will determine the positional relationship between the position of the target feature group in the feature space and the optimal hyperplane, such as which side of the hyperplane it is located on, or how far it is from the hyperplane. According to the positional relationship between the target feature group and the optimal hyperplane, the server can generate a monitoring result. This monitoring result is used to indicate the possible working status of the target compact shelving in the future preset time period, such as normal operation, potential failure risk, etc.

[0047] In a possible implementation, based on the positional relationship, a probability value is calculated, the probability value includes a first probability value and a second probability value, the first probability value is used to represent the probability value corresponding to the feature space position on the first side of the hyperplane, and the second probability value is used to represent the probability value corresponding to the feature space position on the second side of the hyperplane, the first side and the second side are two opposite sides of the hyperplane; if it is determined that the feature space position is located on the first side, and the first probability value is greater than or equal to a preset threshold, then it is determined that the monitoring result indicates normal, and then it is determined that the working status of the target compact shelving indicates normal; if it is determined that the feature space position is located on the second side, and the second probability value is greater than or equal to the preset threshold, then it is determined that the monitoring result indicates abnormal, and then it is determined that the working status of the target compact shelving indicates abnormal.

[0048] Specifically, in the support vector machine algorithm, when the input data, that is, the feature space position, is mapped to the high-dimensional feature space, the algorithm calculates the positional relationship of the data point relative to the optimal hyperplane. Based on this positional relationship, the algorithm can further calculate the probability value of the data point being located on one side of the hyperplane. The probability value here is a quantitative representation of the confidence of the classification of the data point. The first probability value represents the probability that the feature space position is located on the first side of the hyperplane. The second probability value represents the probability that the feature space position is located on the second side of the hyperplane. These two probability values ​​are mutually exclusive, that is, their sum should be close to or equal to 1. If the algorithm determines that the feature space position is located on the first side of the hyperplane, and the first probability value of this position, that is, the confidence of being located on the first side is greater than or equal to a preset threshold, which is set based on experience or actual needs, then it can be considered that the classification of this feature space position belonging to the first side is reliable. Among them, if the feature space position is located on the first side of the hyperplane and the first probability value meets the conditions, then it can be considered that the monitoring result indicates that the working state of the target compact shelving is normal.

[0049] Similarly, if the algorithm determines that the feature space position is located on the second side of the hyperplane, and the second probability value of this position, that is, the confidence level of being located on the second side is greater than or equal to the preset threshold, then the classification of this feature space position belonging to the second side can be considered reliable. Among them, if the feature space position is located on the second side of the hyperplane and the second probability value meets the conditions, then it can be considered that the monitoring result indicates that the working state of the target compact shelving is abnormal.

[0050] S140: If it is determined that the working status indicates an abnormality, a corresponding control strategy is generated.

[0051] Specifically, once the server determines that the working state is abnormal, it will generate one or more control strategies based on the preset control strategy correspondence. These control strategies are designed to resolve or alleviate the current working state abnormality, ensure that the target compact shelving can resume normal operation or at least reduce the impact of the abnormal state on the overall system. Control strategies may include sending alarms to notify administrators, automatically adjusting environmental parameters, starting backup equipment, shutting down or restarting abnormal equipment, etc.

[0052] Therefore, by obtaining multi-dimensional environmental data such as temperature, humidity, light and vibration, the server can fully understand the environmental conditions of the target compact shelving. These parameters are crucial for evaluating whether the storage environment of the compact shelving is suitable and preventing potential failures. The time series prediction algorithm is used to predict the environment within a preset time period, so that the server can respond before the environment changes. This prediction capability helps to detect possible environmental problems in a timely manner, so that measures can be taken in advance to avoid damage to the compact shelving and its stored items. Based on the predicted environmental data, the support vector machine algorithm is used to determine the working status of the target compact shelving. This method not only improves the accuracy of judgment, but also can automatically adapt to the working status of the compact shelving under different environmental conditions, reducing the possibility of manual intervention and misjudgment. When the server determines that the working status of the compact shelving indicates an abnormality, it can quickly generate a corresponding control strategy. This rapid response mechanism helps to solve problems in a timely manner and prevent problems from further deteriorating, thereby ensuring the safety and stability of the compact shelving and its stored items. Through the automated and intelligent monitoring and prediction server, the cost and time of manual monitoring can be significantly reduced, and management efficiency can be improved. At the same time, the accuracy and reliability of the server are also higher, which can provide users with more accurate and reliable data support. By real-time monitoring and predicting environmental changes, the server can promptly detect and prevent potential risk factors. This preventive management strategy helps reduce the company's operating costs and risks. Therefore, it is convenient to improve the electrical control efficiency of the compact shelving.

[0053] In one possible implementation, refer to Figure 2 , Figure 2Another flow chart of a method for controlling the electrical operation of a compact rack provided in an embodiment of the present application. If it is determined that the working state indicates an abnormality, a corresponding control strategy is generated, specifically including steps S210 to S220, the steps are as follows: S210, if it is determined that the working state indicates an abnormal temperature, a corresponding temperature control strategy is generated; S220, the temperature control strategy is sent to the fan device to control the fan device to cool down the target compact rack according to the temperature control strategy.

[0054] Specifically, when the server determines that the operating status of the target compact rack indicates an abnormal temperature, it generates a special temperature control strategy. Temperature control strategies include adjusting the speed of the fan, turning on additional cooling equipment, shutting down or reducing the power consumption of some servers on the compact rack to reduce heat, etc. The temperature control strategy generated by the server needs to be executed, and the fan device is one of the common heat dissipation devices. Therefore, the server will send this temperature control policy to the system or module that controls the fan device. After receiving the temperature control strategy, the fan device will adjust its operating status according to the instructions in the strategy, such as increasing the speed to increase air flow, thereby helping the target compact rack to dissipate heat and cool down.

[0055] In an embodiment of the present application, the control strategies corresponding to other environmental data anomalies may include: if the humidity is too high, a dehumidification device such as a dehumidifier or the dehumidification mode of the air conditioner may be started. At the same time, the sealing of the electrical cabinet and the compact shelving may be checked to ensure that there is no intrusion of external moisture. If the light is too strong, the lighting equipment in the electrical cabinet may be turned off or dimmed. Furthermore, it is ensured that the adjustment of the lighting system meets the energy-saving requirements and protects the electronic equipment in the compact shelving from the influence of light. If the vibration is abnormal, the vibration data is continuously monitored, and an early warning is triggered when the vibration reaches a dangerous level to prevent equipment damage or data loss.

[0056] In one possible implementation, training data is determined based on historical electrical control data of a target compact shelving system; a sliding window is used to extract target time points in the training data, as well as statistical features corresponding to the target time points, the statistical features including mean, standard deviation, maximum value, minimum value, and time slope; time series features are generated based on the mean, standard deviation, maximum value, minimum value, and time slope; the time series features are used to train an initial model to obtain a correspondence between the time series features and labels, the labels including normal and abnormal; the initial model is parameter optimized, and through repeated iterations, a preset time series model that meets preset standards or converges is obtained.

[0057] Specifically, first, the server selects a data set for training the model from the historical electrical control data of the target compact shelving. These data contain the electrical parameters of the compact shelving at different time points, such as voltage, current, power, etc., as well as possible abnormal markers. Sliding window is a time series data processing technology that can slide a fixed-size window on the time series to calculate the statistical characteristics of the data in the window. In this process, for each target time point, that is, the center point of the window, the corresponding statistical characteristics are calculated, including the mean, standard deviation, maximum value, minimum value, and time slope. The time slope refers to the trend of the data in the window over time, which can be calculated by linear regression and other methods. The server combines the above statistical features to form a time series feature vector for each target time point. The server uses these time series feature vectors as input and the corresponding labels as output to train the initial model. The initial model can be any machine learning model suitable for time series data, such as support vector machine, random forest, neural network, etc. Through the training process, the model learns the corresponding relationship between time series features and labels, that is, it can predict the output label based on the input time series features. During the training process, the model's prediction results are made more accurate by adjusting the model's parameters, such as weights and biases. The server iterates the training process repeatedly and continuously adjusts the model parameters until the model meets the preset accuracy, recall and other evaluation criteria, or reaches a convergence state, that is, the model performance is no longer significantly improved.

[0058] The present application also provides a compact shelving electrical control device, referring to Figure 3 , Figure 3 A module schematic diagram of a compact shelving electrical control device provided in an embodiment of the present application. The device is a server, and the server includes an acquisition module 31 and a processing module 32, wherein the acquisition module 31 acquires the first environmental data of the current environment of the target compact shelving, and the first environmental data includes temperature data, humidity data, light data, and vibration data; the processing module 32 uses a time series prediction algorithm to predict the environment of the target compact shelving within a preset time period to obtain second environmental data; the processing module 32 uses a support vector machine algorithm to determine the working state of the target compact shelving based on the second environmental data; if the processing module 32 determines that the working state indicates an abnormality, it generates a corresponding control strategy.

[0059] In a possible implementation, the acquisition module 31 acquires the first environmental data of the current environment of the target compact shelving, specifically including: the acquisition module 31 receives the original temperature data of the current environment of the target compact shelving sent by the temperature sensor; the acquisition module 31 receives the original humidity data of the current environment of the target compact shelving sent by the humidity sensor; the acquisition module 31 receives the original light data of the current environment of the target compact shelving sent by the light sensor; the acquisition module 31 receives the original vibration data of the current environment of the target compact shelving sent by the vibration sensor; the processing module 32 preprocesses the original temperature data, the original humidity data, the original light data and the original vibration data to obtain the first environmental data, and the preprocessing includes denoising, filtering and normalization.

[0060] In a possible implementation, the processing module 32 uses a time series prediction algorithm to predict the environment of the target compact shelving within a preset time period to obtain second environmental data, specifically including: the processing module 32 inputs the first environmental data into a preset time series model to generate an environmental feature vector, and the preset time series model is pre-constructed by the time series prediction algorithm; the processing module 32 determines the time feature vector according to the preset time period; the processing module 32 predicts the environmental feature vector and the time feature vector through the preset time series model to generate a pointing environment sequence; the processing module 32 generates the second environmental data according to the pointing environment sequence.

[0061] In a possible implementation, the processing module 32 determines the working status of the target compact shelving based on the second environmental data using a support vector machine algorithm, specifically including: the processing module 32 uses a mean filling method to process missing values ​​in the second environmental data to obtain a target feature group; the processing module 32 calculates the target feature group through a support vector machine algorithm to obtain a feature space position; the processing module 32 determines the positional relationship between the feature space position and the hyperplane corresponding to the support vector machine algorithm; the processing module 32 generates a monitoring result based on the positional relationship, and the monitoring result is used to indicate the working status of the target compact shelving.

[0062] In a possible embodiment, the processing module 32 calculates a probability value based on the position relationship, and the probability value includes a first probability value and a second probability value, the first probability value is used to represent the probability value corresponding to the feature space position on the first side of the hyperplane, and the second probability value is used to represent the probability value corresponding to the feature space position on the second side of the hyperplane, and the first side and the second side are two opposite sides of the hyperplane; if the processing module 32 determines that the feature space position is located on the first side and the first probability value is greater than or equal to a preset threshold, then it is determined that the monitoring result indicates normal, and then it is determined that the working status of the target compact shelving indicates normal; if the processing module 32 determines that the feature space position is located on the second side and the second probability value is greater than or equal to the preset threshold, then it is determined that the monitoring result indicates abnormal, and then it is determined that the working status of the target compact shelving indicates abnormal.

[0063] In a possible implementation, if the processing module 32 determines that the working status indicates an abnormality, it generates a corresponding control strategy, specifically including: if the processing module 32 determines that the working status indicates a temperature abnormality, it generates a corresponding temperature control strategy; the processing module 32 sends the temperature control strategy to the fan device to control the fan device to cool down the target compact shelving according to the temperature control strategy.

[0064] In one possible implementation, the processing module 32 determines the training data based on the historical electrical control data of the target dense shelving; the processing module 32 uses a sliding window to extract the target time point in the training data, and the statistical features corresponding to the target time point, the statistical features including mean, standard deviation, maximum value, minimum value and time slope; the processing module 32 generates time series features based on the mean, standard deviation, maximum value, minimum value and time slope; the processing module 32 uses the time series features to train the initial model to obtain the correspondence between the time series features and the labels, the labels including normal and abnormal; the processing module 32 optimizes the parameters of the initial model, and through repeated iterations, obtains a preset time series model that meets the preset standards or converges.

[0065] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0066] The present application also provides an electronic device, referring to Figure 4 , Figure 4The electronic device may include: at least one processor 41 , at least one network interface 44 , a user interface 43 , a memory 45 , and at least one communication bus 42 .

[0067] The communication bus 42 is used to realize the connection and communication between these components.

[0068] The user interface 43 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 43 may also include a standard wired interface and a wireless interface.

[0069] The network interface 44 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0070] Among them, the processor 41 may include one or more processing cores. The processor 41 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 45, and calling data stored in the memory 45. Optionally, the processor 41 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 41 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 41, and it can be implemented separately through a chip.

[0071] Among them, the memory 45 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 45 includes a non-transitory computer-readable storage medium. The memory 45 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 45 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 45 may also be optionally at least one storage device located away from the aforementioned processor 41. As Figure 4 As shown, the memory 45 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program of a compact rack electrical control method.

[0072] exist Figure 4 In the electronic device shown, the user interface 43 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 41 can be used to call an application program for a compact shelving electrical control method stored in the memory 45. When executed by one or more processors, the electronic device executes one or more methods such as those in the above-mentioned embodiments.

[0073] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0074] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.

[0075] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0076] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0077] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0078] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0079] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0080] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, it will be easy for those skilled in the art to think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for electrical control of a compact rack, characterized in that: The method comprises: Acquire first environmental data of the current environment of the target compact rack, wherein the first environmental data includes temperature data, humidity data, light data, and vibration data; A time series prediction algorithm is used to predict the environment of the target compact rack within a preset time period to obtain second environment data; According to the second environmental data, a support vector machine algorithm is used to determine the working state of the target compact shelving; If it is determined that the working status indicates an abnormality, a corresponding control strategy is generated.

2. The electrical control method for compact racks according to claim 1, characterized in that: The step of obtaining first environment data of the current environment of the target compact rack specifically includes: Receive the original temperature data of the current environment of the target compact rack sent by the temperature sensor; Receiving raw humidity data of the current environment of the target compact rack sent by a humidity sensor; Receiving original light data of the current environment of the target compact rack sent by the light sensor; Receiving original vibration data of the current environment of the target compact rack sent by a vibration sensor; The original temperature data, the original humidity data, the original illumination data, and the original vibration data are preprocessed to obtain the first environmental data, wherein the preprocessing includes denoising, filtering, and normalization processing.

3. The electrical control method for compact racks according to claim 1, characterized in that: The use of a time series prediction algorithm to predict the environment of the target compact rack within a preset time period to obtain the second environment data specifically includes: Inputting the first environmental data into a preset time series model to generate an environmental feature vector, wherein the preset time series model is pre-constructed by the time series prediction algorithm; Determining a time feature vector according to the preset time period; Predicting the environment feature vector and the time feature vector through the preset time series model to generate a pointing environment sequence; The second environment data is generated according to the pointing environment sequence.

4. The electrical control method for compact racks according to claim 1, characterized in that: Determining the working state of the target compact rack using a support vector machine algorithm according to the second environmental data specifically includes: Using the mean filling method to process missing values ​​of the second environmental data to obtain a target feature group; The target feature group is calculated by the support vector machine algorithm to obtain a feature space position; Determining the positional relationship between the feature space position and the hyperplane corresponding to the support vector machine algorithm; A monitoring result is generated according to the positional relationship, and the monitoring result is used to indicate the working status of the target compact shelving.

5. The electrical control method for compact racks according to claim 4, characterized in that: The method further comprises: Based on the positional relationship, a probability value is calculated, the probability value comprising a first probability value and a second probability value, the first probability value being used to represent a probability value corresponding to the first side of the feature space position of the hyperplane, the second probability value being used to represent a probability value corresponding to the second side of the feature space position of the hyperplane, the first side and the second side being two opposite sides of the hyperplane; If it is determined that the feature space position is located on the first side, and the first probability value is greater than or equal to a preset threshold, it is determined that the monitoring result indicates normal, and it is determined that the working state of the target compact shelving indicates normal; If it is determined that the feature space position is located on the second side, and the second probability value is greater than or equal to the preset threshold, it is determined that the monitoring result indicates an abnormality, and it is determined that the working state of the target compact shelving indicates an abnormality.

6. The electrical control method for compact racks according to claim 1, characterized in that: If it is determined that the working state indicates an abnormality, a corresponding control strategy is generated, specifically including: If it is determined that the working state indicates abnormal temperature, generating a corresponding temperature control strategy; The temperature control strategy is sent to the fan device to control the fan device to cool down the target compact rack according to the temperature control strategy.

7. The electrical control method for compact racks according to claim 3, characterized in that: The method further comprises: Determining training data according to the historical electrical control data of the target compact rack; Using a sliding window to extract the target time point in the training data and the statistical features corresponding to the target time point, the statistical features including mean, standard deviation, maximum value, minimum value and time slope; Generate the time series feature according to the mean, the standard deviation, the maximum value, the minimum value and the time slope; The time series features are used to train the initial model to obtain a corresponding relationship between the time series features and labels, wherein the labels include normal and abnormal; The parameters of the initial model are optimized, and through repeated iterations, the preset time series model that meets the preset standard or converges is obtained.

8. An electrical control device for a compact shelving system, characterized in that: The electrical control device for the compact shelving includes an acquisition module and a processing module, wherein: The acquisition module (31) is used to acquire first environmental data of the current environment of the target compact rack, wherein the first environmental data includes temperature data, humidity data, light data and vibration data; The processing module (32) is used to use a time series prediction algorithm to predict the environment in which the target compact rack is located within a preset time period to obtain second environment data; The processing module (32) is further used to determine the working state of the target compact rack using a support vector machine algorithm according to the second environmental data; The processing module (32) is further configured to generate a corresponding control strategy if it is determined that the working state indicates an abnormality.

9. An electronic device, characterized in that: The electronic device comprises a processor (41), a memory (45), a user interface (43) and a network interface (44), wherein the memory (45) is used to store instructions, the user interface (43) and the network interface (44) are both used to communicate with other devices, and the processor (41) is used to execute the instructions stored in the memory (45) so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is performed.

Images