Electric control cabinet explosion-proof detection method and system for intelligent warehouse

Abstract

The invention discloses an electric control cabinet explosion-proof detection method and system for an intelligent warehouse, and relates to the technical field of data processing, and the method comprises the steps: generating warehouse characteristic temperature and warehouse characteristic air pressure, and configuring the constant air pressure of an electric control cabinet; receiving electrical working parameters of the electric control cabinet, generating multiple groups of continuous electrical working parameters of the electric control cabinet, and training to generate an air pressure change prediction curve in combination with warehouse characteristic temperature; monitoring air pressure in the electric control cabinet, and constructing an air pressure change reference curve; and performing deviation analysis on the air pressure change prediction curve and the air pressure change reference curve to generate an air pressure control deviation coefficient, and adding the air pressure control deviation coefficient into an electric control cabinet explosion-proof detection result. The technical problems that in the prior art, explosion-proof detection of a traditional electric control cabinet usually depends on the air pressure deviation threshold value, the control precision is low, and the explosion-proof effect is unstable are solved, and the technical effect of improving the explosion-proof performance of the electric control cabinet by dynamically predicting the air pressure change in the electric control cabinet and dynamically adjusting the air pressure in real time is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an explosion-proof detection method and system for an electric control cabinet used in an intelligent warehouse. Background Art

[0002] Electrical control cabinets are usually used in industrial automation control in flammable and explosive environments. Therefore, in order to ensure work safety and production efficiency, the control cabinet must take explosion-proof measures to avoid explosion accidents. Traditional explosion-proof detection of electrical control cabinets usually adopts PID control strategy to ensure that the positive pressure inside the electrical control cabinet is maintained at a certain constant value. The disadvantage is that it usually adjusts when the air pressure deviates from a certain threshold, and the control accuracy is low, resulting in unstable explosion-proof effect. Summary of the invention

[0003] The present application provides an explosion-proof detection method and system for electric control cabinets in smart warehouses, which are used to solve the technical problems in the prior art that traditional explosion-proof detection of electric control cabinets usually relies on air pressure deviation thresholds, has low control accuracy, and unstable explosion-proof effect.

[0004] The first aspect of the present application provides an explosion-proof detection method for an electric control cabinet in an intelligent warehouse, the method comprising: when the intelligent warehouse generates storage item change information, tracing the historical storage environment of the storage item type to generate a warehouse characteristic temperature and a warehouse characteristic air pressure; configuring a constant air pressure of the electric control cabinet according to the warehouse characteristic air pressure; interacting with the electric control cabinet, receiving the electrical working parameters of the electric control cabinet, performing control modal segmentation on the electrical working parameters of the electric control cabinet, and generating multiple sets of continuous electrical working parameters of the electric control cabinet; in combination with the warehouse characteristic temperature, sequentially retrieving the multiple sets of continuous electrical working parameters of the electric control cabinet, activating the air pressure change prediction channel for training, and generating an air pressure change prediction curve; monitoring the air pressure inside the electric control cabinet, and constructing an air pressure change baseline curve; performing deviation analysis on the air pressure change prediction curve and the air pressure change baseline curve to generate an air pressure control deviation coefficient; and adding the air pressure control deviation coefficient to the explosion-proof detection result of the electric control cabinet.

[0005] According to a second aspect of the present application, there is provided an explosion-proof detection system for electric control cabinets in smart warehouses, the system comprising: a warehouse characteristic parameter generation module, the warehouse characteristic parameter generation module being used to perform tracing of the historical storage environment of the storage item type when the smart warehouse generates storage item change information, and generating warehouse characteristic temperature and warehouse characteristic air pressure; an electric control cabinet constant air pressure configuration module, the electric control cabinet constant air pressure configuration module being used to configure the electric control cabinet constant air pressure according to the warehouse characteristic air pressure; an electrical working parameter generation module, the electrical working parameter generation module being used to interact with the electric control cabinet, receive the electrical working parameters of the electric control cabinet, perform control mode segmentation on the electrical working parameters of the electric control cabinet, and generate multiple sets of continuous electrical working parameters of the electric control cabinet; and an air pressure change prediction curve. A generation module, the air pressure change prediction curve generation module is used to combine the warehouse characteristic temperature, sequentially retrieve the multiple groups of continuous electrical working parameters of the electric control cabinet, activate the air pressure change prediction channel for training, and generate an air pressure change prediction curve; an air pressure change reference curve construction module, the air pressure change reference curve construction module is used to monitor the air pressure inside the electric control cabinet and construct an air pressure change reference curve; an air pressure control deviation coefficient generation module, the air pressure control deviation coefficient generation module is used to perform deviation analysis on the air pressure change prediction curve and the air pressure change reference curve, and generate an air pressure control deviation coefficient; an electric control cabinet explosion-proof detection result acquisition module, the electric control cabinet explosion-proof detection result acquisition module is used to add the air pressure control deviation coefficient into the electric control cabinet explosion-proof detection result.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The present application provides an explosion-proof detection method for electric control cabinets for smart warehouses, which relates to the field of data processing technology. The method generates multiple sets of continuous electrical working parameters of the electric control cabinet by receiving the electrical working parameters of the electric control cabinet, and trains and generates an air pressure change prediction curve in combination with the characteristic temperature of the warehouse. The air pressure inside the electric control cabinet is monitored, and an air pressure change reference curve is constructed. The deviation analysis of the air pressure change prediction curve and the air pressure change reference curve is performed to generate an air pressure control deviation coefficient, which is added to the explosion-proof detection result of the electric control cabinet. The technical problems in the prior art that traditional explosion-proof detection of electric control cabinets usually relies on air pressure deviation thresholds, has low control accuracy, and has unstable explosion-proof effects are solved, and the technical effect of improving the explosion-proof performance of the electric control cabinet is achieved by dynamically predicting the air pressure changes inside the electric control cabinet and dynamically adjusting the air pressure in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A schematic diagram of a method for detecting explosion-proof electrical control cabinets in a smart warehouse provided in an embodiment of the present application;

[0010] Figure 2 A schematic diagram of a process for generating multiple sets of continuous electrical operating parameters of an electric control cabinet in an explosion-proof detection method for an electric control cabinet in a smart warehouse provided in an embodiment of the present application;

[0011] Figure 3 A schematic diagram of a flow chart of generating an air pressure change prediction curve in an explosion-proof detection method for an electric control cabinet in a smart warehouse provided in an embodiment of the present application;

[0012] Figure 4 A schematic diagram of the structure of an explosion-proof detection system for an electric control cabinet for a smart warehouse provided in an embodiment of the present application.

[0013] Explanation of the accompanying drawings: warehouse characteristic parameter generation module 11, electric control cabinet constant air pressure configuration module 12, electrical working parameter generation module 13, air pressure change prediction curve generation module 14, air pressure change reference curve construction module 15, air pressure control deviation coefficient generation module 16, electric control cabinet explosion-proof detection result acquisition module 17. DETAILED DESCRIPTION

[0014] The present application provides an explosion-proof detection method for electric control cabinets in smart warehouses, which is used to solve the technical problems in the prior art that traditional explosion-proof detection of electric control cabinets usually relies on air pressure deviation thresholds, has low control accuracy, and unstable explosion-proof effect.

[0015] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0016] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0017] Embodiment 1

[0018] like Figure 1 As shown, the present application provides an explosion-proof detection method for an electric control cabinet in a smart warehouse, the method comprising:

[0019] P10: When the smart warehouse generates storage item change information, it performs traceability on the historical storage environment of the storage item type and generates warehouse characteristic temperature and warehouse characteristic air pressure;

[0020] Specifically, when the storage items in the target smart warehouse change, the historical storage environment information is traced according to the type of storage items. That is, through data mining, the common environmental information of each type of storage items is screened out from the historical storage environment information, including the common storage temperature and the common storage air pressure. This is used as the warehouse characteristic temperature and the warehouse characteristic air pressure, which can be used as a reference for the parameter setting of the electric control cabinet.

[0021] P20: According to the characteristic air pressure of the warehouse, configure the electric control cabinet to maintain constant air pressure;

[0022] It should be understood that the constant air pressure of the electric control cabinet of the target smart warehouse is configured with reference to the characteristic air pressure of the warehouse. Generally, the constant air pressure of the electric control cabinet should be greater than the characteristic air pressure of the warehouse to ensure the safety of the electrical equipment in the electric control cabinet.

[0023] P30: Interactive electric control cabinet, receiving the electric working parameters of the electric control cabinet, performing control mode segmentation on the electric working parameters of the electric control cabinet, and generating multiple sets of continuous electric working parameters of the electric control cabinet;

[0024] Further, such as Figure 2 As shown, step P30 of the embodiment of the present application also includes:

[0025] P31: The electrical operating parameters of the electric control cabinet include the electrical operating parameters of the first timing electric control cabinet and the electrical operating parameters of the second timing electric control cabinet, wherein the first timing and the second timing are adjacent timings;

[0026] P32: performing deviation distance evaluation on the electrical working parameters of the first sequential electric control cabinet and the electrical working parameters of the second sequential electric control cabinet to generate a modal distance coefficient;

[0027] Furthermore, step P32 of the embodiment of the present application also includes:

[0028] P32-1: Traverse the electrical working parameter attributes and configure the attribute deviation threshold;

[0029] P32-2: Calculate the deviation of the electrical working parameters of the first sequential electric control cabinet and the electrical working parameters of the second sequential electric control cabinet to generate a deviation modulus of the electrical working parameters;

[0030] P32-3: Extract the mean value of the modulus of the electrical working parameter deviation that is greater than or equal to the attribute deviation threshold, and set it as the modal distance coefficient.

[0031] P33: Based on the modal distance threshold and in combination with the modal distance coefficient, adjacent time series clustering is performed on the electrical operating parameters of the electric control cabinet to generate multiple groups of initial continuous electrical operating parameters of the electric control cabinet;

[0032] P34: Traverse the multiple groups of initial continuous electrical control cabinet electrical working parameters to extract centralized values ​​of the electrical working parameters, and generate the multiple groups of continuous electrical control cabinet electrical working parameters.

[0033] Optionally, an interactive target electric control cabinet is used, and electrical operating parameters of the electric control cabinet are received, that is, operating parameters pre-configured in the target electric control cabinet, such as operating voltage, operating current, operating temperature, protection level, etc. The electrical operating parameters of the electric control cabinet include multiple groups of electrical operating parameters in multiple different time periods. Exemplarily, the electrical operating parameters of the electric control cabinet include electrical operating parameters of a first-sequence electric control cabinet and electrical operating parameters of a second-sequence electric control cabinet, and the first sequence and the second sequence are two adjacent time periods.

[0034] Furthermore, the deviation distance of the electrical working parameters in any two adjacent time sequences is evaluated respectively. Exemplarily, the deviation distance of the electrical working parameters of the first time sequence electric control cabinet and the electrical working parameters of the second time sequence electric control cabinet is evaluated. First, the electrical working parameter attributes are traversed, and corresponding attribute deviation thresholds, that is, maximum parameter deviations, such as pressure deviation thresholds, are configured for each electrical parameter. Further, deviation calculations are performed on the electrical working parameters of the first time sequence electric control cabinet and the electrical working parameters of the second time sequence electric control cabinet, respectively, such as calculating the working current deviation and working voltage deviation of the first time sequence and the second time sequence, and generating corresponding electrical working parameter deviation modulus values. Similarly, the same method is used to calculate the deviation of the electrical working parameters of any two adjacent time sequences, and multiple electrical working parameter deviation modulus values ​​are generated. Further, the modulus values ​​of the electrical working parameter deviation modulus values ​​greater than or equal to the attribute deviation threshold values ​​are extracted, and the modal distance coefficients of the corresponding working parameters are obtained by calculating the mean of the modulus values.

[0035] Furthermore, taking the modal distance threshold as the clustering standard, adjacent time series clustering is performed on the electrical working parameters of the electric control cabinet with reference to the modal distance coefficient, and the electrical working parameters whose modal distance coefficients are at the same modal distance threshold are classified into one category, and the electrical working parameters at different modal distance thresholds are classified into different categories, that is, the electrical working parameters of adjacent time series with smaller deviations are classified into one category, and multiple groups of initial continuous electrical working parameters of the electric control cabinet are generated, and each group of initial continuous electrical working parameters of the electric control cabinet contains multiple working parameter sequences with different attributes.

[0036] Furthermore, a central trend analysis is performed on the multiple groups of initial continuous electrical working parameters of the electric control cabinets respectively. First, discrete values ​​are identified by using an outlier analysis method. For example, the quartile range method is used to screen out outliers in the electrical working parameters of each attribute in any group of initial continuous electrical working parameters of the electric control cabinet and delete them. Then, the mean is calculated for the remaining values ​​to obtain the central value of the electrical working parameters of each attribute. Similarly, the central value of the electrical working parameters of each attribute in the multiple groups of initial continuous electrical working parameters of the electric control cabinets is obtained to generate the multiple groups of continuous electrical working parameters of the electric control cabinets.

[0037] P40: In combination with the warehouse characteristic temperature, the plurality of sets of continuous electrical control cabinet electrical working parameters are retrieved in sequence, the air pressure change prediction channel is activated for training, and an air pressure change prediction curve is generated;

[0038] Further, such as Figure 3 As shown, step P40 of the embodiment of the present application also includes:

[0039] P41: Based on big data, the warehouse temperature monitoring data set, the electrical control cabinet electrical working parameter record data set, the initial air pressure record data set and the air pressure change curve monitoring data set are collected;

[0040] P42: Based on the long short-term memory neural network, build the topological structure of the pressure change prediction channel;

[0041] P43: Constructing the air pressure change prediction loss function:

[0042]

[0043] Among them, LOSS represents the training loss value, y ij The predicted value of the air pressure at the jth moment, y, represents the output value of the i-th training. ij0 The air pressure monitoring data at the jth moment of the air pressure change curve monitoring data set of the i-th training, M represents the preconfigured prediction duration, and N represents the number of training times for statistical training loss;

[0044] P44: According to the air pressure change prediction loss function, the warehouse temperature monitoring data set, the electrical control cabinet electrical working parameter recording data set, the initial air pressure recording data set and the air pressure change curve monitoring data set are retrieved to configure the air pressure change prediction channel topology structure, and generate the air pressure change prediction channel;

[0045] In a possible embodiment of the present application, electrical working parameters of electric control cabinets in sample intelligent warehouses are collected based on big data to obtain a warehouse temperature monitoring data set, an electric control cabinet electrical working parameter recording data set, an initial air pressure recording data set, and an air pressure change curve monitoring data set. Furthermore, based on a long short-term memory neural network, an air pressure change prediction channel topology structure is constructed. The long short-term memory neural network is a time recursive neural network with long-term memory capabilities, and its network structure consists of one or more units with forgettable and memory functions, and is suitable for processing and predicting important events with very long intervals and delays in time series.

[0046] Furthermore, the pressure change prediction loss function is constructed:

[0047]

[0048] Among them, LOSS represents the training loss value, y ij The predicted value of the air pressure at the jth moment, y, represents the output value of the i-th training. ij0The j-th moment air pressure monitoring data of the air pressure change curve monitoring data set of the i-th training, M represents the preconfigured prediction duration, N represents the number of training times of statistical training loss, according to the air pressure change prediction loss function, the warehouse temperature monitoring data set, the electrical control cabinet electrical working parameter record data set, the initial air pressure record data set and the air pressure change curve monitoring data set are retrieved as training data, the air pressure change prediction channel topology structure is trained, and the topology structure is adjusted according to the output result until the training loss value meets the preset loss requirement, indicating that the air pressure change prediction channel topology structure has reached convergence, and the air pressure change prediction channel is generated.

[0049] P45: According to the air pressure change prediction channel, the characteristic temperature of the warehouse and the constant air pressure of the electric control cabinet are received, and the multiple groups of continuous electrical working parameters of the electric control cabinet are retrieved in sequence for training to generate the air pressure change prediction curve.

[0050] Furthermore, step P45 of the embodiment of the present application also includes:

[0051] P45-1: The multiple groups of continuous electric control cabinet electrical working parameters include the first group of electric control cabinet electrical working parameters and the first working duration, the second group of electric control cabinet electrical working parameters and the second working duration, until the Lth group of electric control cabinet electrical working parameters and the Lth working duration;

[0052] P45-2: Activate the air pressure change prediction channel, receive the warehouse characteristic temperature, the electric control cabinet constant air pressure and the first set of electric control cabinet electrical working parameters to perform the prediction of the first working time, and generate a first air pressure change prediction curve, wherein the first air pressure change prediction curve has a first curve end point air pressure;

[0053] P45-3: Activate the air pressure change prediction channel, receive the warehouse characteristic temperature, the first curve endpoint air pressure and the second set of electrical control cabinet electrical working parameters to perform the second working time prediction, and generate a second air pressure change prediction curve, wherein the second air pressure change prediction curve has a second curve endpoint air pressure;

[0054] P45-4: Repeat the iteration until the Lth air pressure change prediction curve is generated;

[0055] P45-5: Connect the first air pressure change prediction curve, the second air pressure change prediction curve, and the Lth air pressure change prediction curve in sequence to generate the air pressure change prediction curve.

[0056] Exemplarily, the characteristic temperature of the warehouse and the constant air pressure of the electric control cabinet are received through the air pressure change prediction channel, and the multiple groups of continuous electrical working parameters of the electric control cabinet are sequentially retrieved as training data to perform air pressure change prediction curve training, wherein the multiple groups of continuous electrical working parameters of the electric control cabinet include a first group of electrical working parameters of the electric control cabinet and a first working duration, a second group of electrical working parameters of the electric control cabinet and a second working duration, until the Lth group of electrical working parameters of the electric control cabinet and the Lth working duration, a total of L groups of electrical working parameters of the electric control cabinet.

[0057] Further, the air pressure change prediction channel is activated, and the warehouse characteristic temperature, the electric control cabinet constant air pressure and the first set of electric control cabinet electrical working parameters are used to predict the air pressure change based on the first working time, and a first air pressure change prediction curve is generated according to the air pressure prediction result. The first air pressure change prediction curve has a first curve end point air pressure, which can be used as the starting point air pressure of the second air pressure change prediction curve. Similarly, the warehouse characteristic temperature and the first curve end point air pressure are received through the air pressure change prediction channel, and the second set of electric control cabinet electrical working parameters are used to predict the air pressure change based on the second working time to generate the second air pressure change prediction curve. Repeat the iteration in this way until the Lth air pressure change prediction curve is generated, and finally the first air pressure change prediction curve, the second air pressure change prediction curve, and the Lth air pressure change prediction curve are connected in chronological order to generate the air pressure change prediction curve.

[0058] P50: Monitor the air pressure inside the electric control cabinet and construct a reference curve of air pressure change;

[0059] Specifically, by installing an air pressure monitoring device inside the electric control cabinet, the air pressure changes inside the electric control cabinet are monitored in real time, and the air pressure monitoring data over a period of time is obtained to draw an air pressure change reference curve, that is, the actual air pressure change curve inside the electric control cabinet, which can be used to verify the accuracy of the air pressure prediction data.

[0060] P60: Perform deviation analysis on the air pressure change prediction curve and the air pressure change reference curve to generate an air pressure control deviation coefficient;

[0061] Furthermore, step P60 of the embodiment of the present application further includes:

[0062] P61: Configure an air pressure deviation threshold, and count the ratio of the number of air pressures in the air pressure change prediction curve and the air pressure change reference curve that are greater than or equal to the air pressure deviation threshold, and set it as the air pressure control deviation coefficient.

[0063] Optionally, an air pressure deviation analysis is performed on the air pressure change prediction curve and the air pressure change reference curve, that is, the difference between the predicted air pressure and the actual air pressure is calculated. First, an air pressure deviation threshold is configured, that is, the minimum deviation between the predicted air pressure and the actual air pressure. Furthermore, the number of air pressure values ​​in the air pressure change prediction curve and the air pressure change reference curve whose air pressure deviation is greater than or equal to the air pressure deviation threshold is counted, and the proportion of the number of air pressure values ​​to the total number of air pressure values ​​is calculated. This is used as the air pressure control deviation coefficient, which can reflect the control deviation of the system.

[0064] P70: Add the air pressure control deviation coefficient into the explosion-proof test result of the electric control cabinet.

[0065] Furthermore, step P70 of the embodiment of the present application further includes:

[0066] P71: When the air pressure control deviation coefficient is less than or equal to the control deviation coefficient threshold, an electric control cabinet air pressure control stability mark is generated and added to the electric control cabinet explosion-proof detection result;

[0067] P72: When the air pressure control deviation coefficient is greater than the control deviation coefficient threshold, the air pressure control of the electric control cabinet is checked multiple times with the characteristic temperature of the warehouse and the constant air pressure of the electric control cabinet as constraints, and the air pressure control record data of the electric control cabinet is generated, wherein the air pressure control record data of the electric control cabinet includes the record value of the electrical working parameters of the electric control cabinet, the record value of the air pressure control deviation coefficient and the record value of the air pressure deviation vector;

[0068] P73: Taking the electrical working parameter record value of the electric control cabinet and the air pressure control deviation coefficient as input and the air pressure deviation vector record value as output, construct an air pressure deviation vector fitting component;

[0069] P74: Cooperate with the air pressure deviation vector fitting component and the air pressure change prediction channel to perform air pressure control of the electric control cabinet.

[0070] It should be understood that adding the air pressure control deviation coefficient to the explosion-proof detection result of the electric control cabinet can be used to verify the accuracy of air pressure prediction and serve as a reference for adjusting air pressure control parameters in the future. When the air pressure control deviation coefficient is less than or equal to the control deviation coefficient threshold, it means that the air pressure control deviation of the system is within the allowable range, and then an electric control cabinet air pressure control stability mark is generated and added to the explosion-proof detection result of the electric control cabinet to feedback that the current explosion-proof detection result of the electric control cabinet is in a stable state, and no subsequent parameter adjustment is required.

[0071] Optionally, when the air pressure control deviation coefficient is greater than the control deviation coefficient threshold, it means that the air pressure control deviation of the current system exceeds the allowable range and there is a safety risk, then the auxiliary module needs to perform calibration compensation of the air pressure prediction value. Exemplarily, the characteristic temperature of the warehouse and the constant air pressure of the electric control cabinet are constraints, and the electric control cabinet is verified for multiple air pressure control results, that is, the control deviation of multiple air pressure control results is evaluated to generate air pressure control record data of the electric control cabinet. The air pressure control record data of the electric control cabinet includes the record value of the electrical working parameters of the electric control cabinet, the record value of the air pressure control deviation coefficient and the record value of the air pressure deviation vector. The record value of the air pressure deviation vector can reflect whether the air pressure deviation direction is too large or too small.

[0072] Furthermore, the recorded values ​​of the electrical working parameters of the electric control cabinet and the air pressure control deviation coefficient are used as input data, and the recorded values ​​of the air pressure deviation vector are used as output data, and combined with machine learning, such as BP neural network, an air pressure deviation vector fitting component is constructed, and supervised training is performed through the input data and output data until the output of the air pressure deviation vector fitting component reaches convergence, thereby obtaining an air pressure deviation vector fitting component. The air pressure deviation vector fitting component is used as an auxiliary module to calibrate and compensate the output result of the air pressure change prediction channel to achieve air pressure control of the electric control cabinet and obtain a good explosion-proof effect.

[0073] In summary, the embodiments of the present application have at least the following technical effects:

[0074] The present application generates multiple sets of continuous electrical working parameters of the electric control cabinet by receiving the electrical working parameters of the electric control cabinet, and trains and generates an air pressure change prediction curve in combination with the characteristic temperature of the warehouse, monitors the air pressure inside the electric control cabinet, constructs an air pressure change baseline curve, performs deviation analysis on the air pressure change prediction curve and the air pressure change baseline curve, generates an air pressure control deviation coefficient, and adds it to the explosion-proof detection result of the electric control cabinet.

[0075] The technical effect of improving the explosion-proof performance of the electric control cabinet is achieved by dynamically predicting the changes in the air pressure inside the electric control cabinet and dynamically adjusting the air pressure in real time.

[0076] Embodiment 2

[0077] Based on the same inventive concept as the explosion-proof detection method for an electric control cabinet in a smart warehouse in the aforementioned embodiment, Figure 4 As shown, the present application provides an explosion-proof detection system for electric control cabinets used in smart warehouses. The system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0078] A warehouse characteristic parameter generation module 11, which is used to perform tracing of the historical storage environment of the storage item type when the intelligent warehouse generates storage item change information, and generate a warehouse characteristic temperature and a warehouse characteristic air pressure;

[0079] An electric control cabinet constant air pressure configuration module 12, the electric control cabinet constant air pressure configuration module 12 is used to configure the electric control cabinet constant air pressure according to the warehouse characteristic air pressure;

[0080] An electrical working parameter generating module 13, the electrical working parameter generating module 13 is used for interacting with the electric control cabinet, receiving the electrical working parameters of the electric control cabinet, performing control mode segmentation on the electrical working parameters of the electric control cabinet, and generating multiple sets of continuous electrical working parameters of the electric control cabinet;

[0081] An air pressure change prediction curve generating module 14, the air pressure change prediction curve generating module 14 is used to sequentially retrieve the plurality of sets of continuous electric control cabinet electrical working parameters in combination with the warehouse characteristic temperature, activate the air pressure change prediction channel for training, and generate an air pressure change prediction curve;

[0082] An air pressure variation reference curve construction module 15, wherein the air pressure variation reference curve construction module 15 is used to monitor the air pressure inside the electric control cabinet and construct an air pressure variation reference curve;

[0083] An air pressure control deviation coefficient generating module 16, the air pressure control deviation coefficient generating module 16 is used to perform deviation analysis on the air pressure change prediction curve and the air pressure change reference curve to generate an air pressure control deviation coefficient;

[0084] The electric control cabinet explosion-proof detection result obtaining module 17 is used to add the air pressure control deviation coefficient into the electric control cabinet explosion-proof detection result.

[0085] Furthermore, the electrical working parameter generating module 13 is also used to perform the following steps:

[0086] The electrical operating parameters of the electric control cabinet include first-sequence electrical operating parameters of the electric control cabinet and second-sequence electrical operating parameters of the electric control cabinet, wherein the first sequence and the second sequence are adjacent sequences;

[0087] Performing deviation distance evaluation on the electrical operating parameters of the first sequential electric control cabinet and the electrical operating parameters of the second sequential electric control cabinet to generate a modal distance coefficient;

[0088] Based on the modal distance threshold and in combination with the modal distance coefficient, adjacent time series clustering is performed on the electrical operating parameters of the electric control cabinet to generate multiple groups of initial continuous electrical operating parameters of the electric control cabinet;

[0089] The multiple groups of initial continuous electrical control cabinet electrical working parameters are traversed to extract concentrated values ​​of the electrical working parameters, and the multiple groups of continuous electrical control cabinet electrical working parameters are generated.

[0090] Furthermore, the electrical working parameter generating module 13 is also used to perform the following steps:

[0091] Traverse the electrical working parameter attributes and configure the attribute deviation threshold;

[0092] Calculating the deviation of the electrical working parameters of the first sequential electric control cabinet and the electrical working parameters of the second sequential electric control cabinet to generate a deviation modulus of the electrical working parameters;

[0093] The mean value of the modulus of the electrical working parameter deviation whose modulus is greater than or equal to the attribute deviation threshold is extracted and set as the modal distance coefficient.

[0094] Furthermore, the air pressure change prediction curve generating module 14 is also used to perform the following steps:

[0095] Based on big data, we collected warehouse temperature monitoring data sets, electrical control cabinet electrical working parameter record data sets, initial air pressure record data sets, and air pressure change curve monitoring data sets;

[0096] Based on the long short-term memory neural network, build the topological structure of the air pressure change prediction channel;

[0097] Construct the air pressure change prediction loss function:

[0098]

[0099] Among them, LOSS represents the training loss value, y ij The predicted value of the air pressure at the jth moment, y, represents the output value of the i-th training. ij0 The air pressure monitoring data at the jth moment of the air pressure change curve monitoring data set of the i-th training, M represents the preconfigured prediction duration, and N represents the number of training times for statistical training loss;

[0100] According to the air pressure change prediction loss function, the warehouse temperature monitoring data set, the electric control cabinet electrical working parameter recording data set, the initial air pressure recording data set and the air pressure change curve monitoring data set are retrieved to configure the air pressure change prediction channel topology structure, and generate the air pressure change prediction channel;

[0101] According to the air pressure change prediction channel, the characteristic temperature of the warehouse and the constant air pressure of the electric control cabinet are received, and the multiple groups of continuous electrical working parameters of the electric control cabinet are retrieved in sequence for training to generate the air pressure change prediction curve.

[0102] Furthermore, the air pressure change prediction curve generating module 14 is also used to perform the following steps:

[0103] The multiple groups of continuous electric control cabinet electrical working parameters include a first group of electric control cabinet electrical working parameters and a first working duration, a second group of electric control cabinet electrical working parameters and a second working duration, until an Lth group of electric control cabinet electrical working parameters and an Lth working duration;

[0104] activating the air pressure change prediction channel, receiving the warehouse characteristic temperature, the electric control cabinet constant air pressure and the first set of electric control cabinet electrical working parameters to perform the prediction of the first working time, and generating a first air pressure change prediction curve, wherein the first air pressure change prediction curve has a first curve end point air pressure;

[0105] activating the air pressure change prediction channel, receiving the warehouse characteristic temperature, the first curve endpoint air pressure and the second set of electrical control cabinet electrical working parameters to perform the prediction of the second working time, and generating a second air pressure change prediction curve, wherein the second air pressure change prediction curve has a second curve endpoint air pressure;

[0106] Repeat the iteration until the Lth air pressure change prediction curve is generated;

[0107] The first air pressure change prediction curve, the second air pressure change prediction curve, and the Lth air pressure change prediction curve are sequentially connected to generate the air pressure change prediction curve.

[0108] Furthermore, the air pressure control deviation coefficient generating module 16 is further configured to perform the following steps:

[0109] A pressure deviation threshold is configured, and the ratio of the number of pressures in the pressure change prediction curve and the pressure change reference curve that is greater than or equal to the pressure deviation threshold is counted and set as the pressure control deviation coefficient.

[0110] Furthermore, the electric control cabinet explosion-proof detection result obtaining module 17 is also used to perform the following steps:

[0111] When the air pressure control deviation coefficient is less than or equal to the control deviation coefficient threshold, an electric control cabinet air pressure control stability mark is generated and added to the electric control cabinet explosion-proof detection result;

[0112] When the air pressure control deviation coefficient is greater than the control deviation coefficient threshold, the air pressure control of the electric control cabinet is checked multiple times with the characteristic temperature of the warehouse and the constant air pressure of the electric control cabinet as constraints, and the air pressure control record data of the electric control cabinet is generated, wherein the air pressure control record data of the electric control cabinet includes the record value of the electrical working parameters of the electric control cabinet, the record value of the air pressure control deviation coefficient and the record value of the air pressure deviation vector;

[0113] Taking the electrical working parameter record value of the electric control cabinet and the air pressure control deviation coefficient as input and the air pressure deviation vector record value as output, constructing an air pressure deviation vector fitting component;

[0114] The air pressure control of the electric control cabinet is performed in collaboration with the air pressure deviation vector fitting component and the air pressure change prediction channel.

[0115] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0116] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0117] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for explosion-proof detection of electric control cabinets for smart warehouses, characterized in that: include: When the smart warehouse generates storage item change information, it performs traceability on the historical storage environment of the storage item type and generates warehouse characteristic temperature and warehouse characteristic air pressure; According to the characteristic air pressure of the warehouse, the electric control cabinet is configured with constant air pressure; An interactive electric control cabinet receives electric working parameters of the electric control cabinet, performs control mode segmentation on the electric working parameters of the electric control cabinet, and generates multiple sets of continuous electric working parameters of the electric control cabinet; Combined with the warehouse characteristic temperature, the plurality of sets of continuous electrical control cabinet electrical working parameters are retrieved in sequence, the air pressure change prediction channel is activated for training, and an air pressure change prediction curve is generated; Monitor the air pressure inside the electric control cabinet and construct a reference curve of air pressure changes; Performing deviation analysis on the air pressure change prediction curve and the air pressure change reference curve to generate an air pressure control deviation coefficient; The air pressure control deviation coefficient is added into the explosion-proof detection result of the electric control cabinet.

2. The method according to claim 1, characterized in that The interactive electric control cabinet receives the electric working parameters of the electric control cabinet, performs control mode segmentation on the electric working parameters of the electric control cabinet, and generates multiple sets of continuous electric working parameters of the electric control cabinet, including: The electrical operating parameters of the electric control cabinet include first-sequence electrical operating parameters of the electric control cabinet and second-sequence electrical operating parameters of the electric control cabinet, wherein the first sequence and the second sequence are adjacent sequences; Performing deviation distance evaluation on the electrical operating parameters of the first sequential electric control cabinet and the electrical operating parameters of the second sequential electric control cabinet to generate a modal distance coefficient; Based on the modal distance threshold and in combination with the modal distance coefficient, adjacent time series clustering is performed on the electrical operating parameters of the electric control cabinet to generate multiple groups of initial continuous electrical operating parameters of the electric control cabinet; The multiple groups of initial continuous electrical control cabinet electrical working parameters are traversed to extract concentrated values ​​of the electrical working parameters, and the multiple groups of continuous electrical control cabinet electrical working parameters are generated.

3. The method according to claim 2, characterized in that Performing deviation distance evaluation on the electrical operating parameters of the first sequential electric control cabinet and the electrical operating parameters of the second sequential electric control cabinet to generate a modal distance coefficient includes: Traverse the electrical working parameter attributes and configure the attribute deviation threshold; Calculating the deviation of the electrical working parameters of the first sequential electric control cabinet and the electrical working parameters of the second sequential electric control cabinet to generate a deviation modulus of the electrical working parameters; The mean value of the modulus of the electrical working parameter deviation whose modulus is greater than or equal to the attribute deviation threshold is extracted and set as the modal distance coefficient.

4. The method according to claim 1, characterized in that Combined with the warehouse characteristic temperature, the multiple sets of continuous electrical control cabinet electrical working parameters are retrieved in sequence, the air pressure change prediction channel is activated for training, and the air pressure change prediction curve is generated, including: Based on big data, we collected warehouse temperature monitoring data sets, electrical control cabinet electrical working parameter record data sets, initial air pressure record data sets, and air pressure change curve monitoring data sets; Based on the long short-term memory neural network, build the topological structure of the air pressure change prediction channel; Construct the air pressure change prediction loss function: Among them, LOSS represents the training loss value, y ij The predicted value of the air pressure at the jth moment, y, represents the output value of the i-th training. ij0 The air pressure monitoring data at the jth moment of the air pressure change curve monitoring data set of the i-th training, M represents the preconfigured prediction duration, and N represents the number of training times for statistical training loss; According to the air pressure change prediction loss function, the warehouse temperature monitoring data set, the electric control cabinet electrical working parameter recording data set, the initial air pressure recording data set and the air pressure change curve monitoring data set are retrieved to configure the air pressure change prediction channel topology structure, and generate the air pressure change prediction channel; According to the air pressure change prediction channel, the characteristic temperature of the warehouse and the constant air pressure of the electric control cabinet are received, and the multiple groups of continuous electrical working parameters of the electric control cabinet are retrieved in sequence for training to generate the air pressure change prediction curve.

5. The method according to claim 4, characterized in that According to the air pressure change prediction channel, the characteristic temperature of the warehouse and the constant air pressure of the electric control cabinet are received, and the multiple groups of continuous electric control cabinet electrical working parameters are sequentially retrieved for training to generate the air pressure change prediction curve, including: The multiple groups of continuous electric control cabinet electrical working parameters include a first group of electric control cabinet electrical working parameters and a first working duration, a second group of electric control cabinet electrical working parameters and a second working duration, until an Lth group of electric control cabinet electrical working parameters and an Lth working duration; activating the air pressure change prediction channel, receiving the warehouse characteristic temperature, the electric control cabinet constant air pressure and the first set of electric control cabinet electrical working parameters to perform the prediction of the first working time, and generating a first air pressure change prediction curve, wherein the first air pressure change prediction curve has a first curve end point air pressure; activating the air pressure change prediction channel, receiving the warehouse characteristic temperature, the first curve endpoint air pressure and the second set of electrical control cabinet electrical working parameters to perform the prediction of the second working time, and generating a second air pressure change prediction curve, wherein the second air pressure change prediction curve has a second curve endpoint air pressure; Repeat the iteration until the Lth air pressure change prediction curve is generated; The first air pressure change prediction curve, the second air pressure change prediction curve, and the Lth air pressure change prediction curve are sequentially connected to generate the air pressure change prediction curve.

6. The method according to claim 1, characterized in that Performing deviation analysis on the air pressure change prediction curve and the air pressure change reference curve to generate an air pressure control deviation coefficient includes: A pressure deviation threshold is configured, and the ratio of the number of pressures in the pressure change prediction curve and the pressure change reference curve that is greater than or equal to the pressure deviation threshold is counted and set as the pressure control deviation coefficient.

7. The method according to claim 6, characterized in that The air pressure control deviation coefficient is added to the explosion-proof test results of the electric control cabinet, including: When the air pressure control deviation coefficient is less than or equal to the control deviation coefficient threshold, an electric control cabinet air pressure control stability mark is generated and added to the electric control cabinet explosion-proof detection result; When the air pressure control deviation coefficient is greater than the control deviation coefficient threshold, the air pressure control of the electric control cabinet is checked multiple times with the characteristic temperature of the warehouse and the constant air pressure of the electric control cabinet as constraints, and the air pressure control record data of the electric control cabinet is generated, wherein the air pressure control record data of the electric control cabinet includes the record value of the electrical working parameters of the electric control cabinet, the record value of the air pressure control deviation coefficient and the record value of the air pressure deviation vector; Taking the electrical working parameter record value of the electric control cabinet and the air pressure control deviation coefficient as input and the air pressure deviation vector record value as output, constructing an air pressure deviation vector fitting component; The air pressure control of the electric control cabinet is performed in collaboration with the air pressure deviation vector fitting component and the air pressure change prediction channel.

8. An explosion-proof detection system for electric control cabinets used in smart warehouses, characterized in that: The system comprises: A warehouse characteristic parameter generation module, which is used to perform tracing of the historical storage environment of the storage item type when the intelligent warehouse generates storage item change information, and generate warehouse characteristic temperature and warehouse characteristic air pressure; An electric control cabinet constant air pressure configuration module, the electric control cabinet constant air pressure configuration module is used to configure the electric control cabinet constant air pressure according to the warehouse characteristic air pressure; An electrical working parameter generation module, the electrical working parameter generation module is used for interacting with the electric control cabinet, receiving the electrical working parameters of the electric control cabinet, performing control mode segmentation on the electrical working parameters of the electric control cabinet, and generating multiple sets of continuous electrical working parameters of the electric control cabinet; An air pressure change prediction curve generation module, the air pressure change prediction curve generation module is used to sequentially retrieve the multiple sets of continuous electrical control cabinet electrical working parameters in combination with the warehouse characteristic temperature, activate the air pressure change prediction channel for training, and generate an air pressure change prediction curve; An air pressure variation reference curve construction module, which is used to monitor the air pressure inside the electric control cabinet and construct an air pressure variation reference curve; An air pressure control deviation coefficient generating module, the air pressure control deviation coefficient generating module is used to perform deviation analysis on the air pressure change prediction curve and the air pressure change reference curve to generate an air pressure control deviation coefficient; The electric control cabinet explosion-proof detection result acquisition module is used to add the air pressure control deviation coefficient into the electric control cabinet explosion-proof detection result.

Images