An industrial equipment condition monitoring method, device and medium

Abstract

The embodiment of the application discloses an industrial equipment state monitoring method, device and medium. A plurality of preset multi-data fusion sensors respectively collect working data of the industrial equipment, and the collected working data is stored after encryption; real-time receiving of data information uploaded by the plurality of preset multi-data fusion sensors respectively; uploading the received equipment identification code to an identification analysis node for analysis to obtain equipment information corresponding to the equipment identification code; based on the time sequence of the collected working data, the working data uploaded by the plurality of preset multi-data fusion sensors is grouped and compared, the working data in each group is corrected based on the comparison result, and the corrected working data is bound with the equipment information respectively; based on the historical working data and the preset model training library, the bound working data is analyzed, and the running information of the industrial equipment is output based on the analysis result, so that the state of the industrial equipment is monitored through the running information.

Description

Technical Field

[0001] This application relates to the field of industrial internet technology, and in particular to a method, device and medium for monitoring the condition of industrial equipment. Background Technology

[0002] As a core component of industrial development, sensors are crucial for industrial transformation and upgrading, and for improving product quality and reliability. They have wide applications in industrial transformation and upgrading, the Internet of Things (IoT), and artificial intelligence (AI). Achieving industrial interconnection requires building a comprehensive industrial sensor interconnection and collaboration system. This system not only needs to connect machines, equipment, personnel, and materials through a platform, but also needs to aggregate, process, and analyze large amounts of industrial data to provide decision-making support for industrial production, thereby enhancing the intelligence level of manufacturing and industrial enterprises.

[0003] Existing sensors are mainly used in industrial production equipment fault monitoring scenarios, but the types of data collected are limited, the spatial range of a single sensor is limited, and once a sensor fails, the equipment data during the fault period is lost and cannot be recovered, making it difficult to accurately monitor the status of industrial equipment. Summary of the Invention

[0004] This application provides an industrial equipment condition monitoring method, device, and medium to solve the following technical problems: existing sensors collect data of limited types, the spatial range of a single sensor is limited, and once a sensor fails, the equipment data during the failure period is lost and cannot be recovered, making it difficult to accurately monitor the condition of industrial equipment.

[0005] The embodiments of this application adopt the following technical solutions:

[0006] This application provides a method for monitoring the status of industrial equipment. The method includes: collecting operational data from the industrial equipment using multiple pre-set multi-data fusion sensors and encrypting and storing the collected data; receiving data information uploaded by the multiple pre-set multi-data fusion sensors in real time; wherein the data information includes at least the encrypted operational data and the equipment identification code corresponding to the industrial equipment; uploading the received equipment identification code to an identification resolution node for parsing to obtain the equipment information corresponding to the equipment identification code; grouping and comparing the operational data uploaded by the multiple pre-set multi-data fusion sensors according to the chronological order of the collected operational data, correcting the operational data in each group based on the comparison results, and binding the corrected operational data to the equipment information; analyzing the bound operational data based on historical operational data and a pre-set model training library, and outputting the operating information of the industrial equipment based on the analysis results, thereby monitoring the status of the industrial equipment through the operating information.

[0007] This application embodiment receives data from multiple pre-set multi-data fusion sensors in real time, enabling the determination of operational data for each device based on the device information within the data. This allows for comparison of multiple operational data points corresponding to the same device to determine consistency, correcting any inconsistencies and ensuring the accuracy of data for each industrial device. Furthermore, this application embodiment analyzes the bound operational data based on historical operational data and a pre-set model training library to determine the current operating status of the industrial equipment, enabling real-time monitoring and ensuring stable operation.

[0008] In one implementation of this application, multiple preset multi-data fusion sensors are used to collect working data of industrial equipment, and the collected working data is encrypted and stored. Specifically, this includes: collecting working data of the same industrial equipment using multiple preset multi-data fusion sensors; dividing the working data corresponding to the multiple preset multi-data fusion sensors into a first array and a second array; encrypting the working data corresponding to the multiple preset multi-data fusion sensors based on the first array, the second array, and a preset key; and storing the encrypted working data in the preset storage space corresponding to the multiple preset multi-data fusion sensors.

[0009] In one implementation of this application, working data corresponding to multiple preset multi-data fusion sensors are encrypted based on a first array, a second array, and a preset key. Specifically, this includes: performing a first encryption process on the preset first subkey and the first array to obtain a third array; performing a second encryption process on the preset second subkey and the second array to obtain a fourth array; performing an XOR process on the third array and the fourth array to obtain a fifth array, and performing a shift process on the fifth array; encrypting the fifth array with the preset third subkey to obtain a sixth array; performing an XOR process on the fourth array and the sixth array to obtain a seventh array, performing a shift process on the seventh array, and encrypting the seventh array with the preset fourth subkey; until the number of subkeys participating in the encryption process is greater than the preset number of subkeys, thereby completing the encryption of the working data.

[0010] In one implementation of this application, before receiving data information uploaded by multiple pre-set multi-data fusion sensors in real time, the method further includes: generating an internal code for the industrial equipment based on the production base information and type of the industrial equipment; wherein the production base information includes at least one of the production city code and production base serial number; obtaining pre-set node codes corresponding to the top-level node, second-level node, and enterprise node respectively, and generating an identification prefix code for the industrial equipment based on the pre-set node codes; combining the internal code and the identification prefix code according to a preset order to obtain a reference equipment identification code for the industrial equipment; uploading the reference equipment identification code to the parsing second-level node for authentication and registration of the reference equipment identification code by the parsing second-level node; and using the reference equipment identification code as the equipment identification code of the industrial equipment after receiving the authentication pass information sent by the parsing second-level node.

[0011] In one implementation of this application, the received device identification code is uploaded to an identifier resolution node for parsing to obtain the device information corresponding to the device identification code. Specifically, this includes: uploading the received device identification code corresponding to the industrial equipment to the identifier resolution node, so that the identifier resolution node can parse the device identification code corresponding to the industrial equipment to obtain the production base serial number and hash value corresponding to the device identification code; determining the storage block corresponding to the industrial equipment in the blockchain using the production base serial number; and finding the industrial equipment information corresponding to the device identification code based on the hash value and the storage block.

[0012] In one implementation of this application, based on the chronological order of data acquisition, the working data uploaded by multiple preset multi-data fusion sensors are grouped and compared. Based on the comparison results, the working data in each group is corrected. Specifically, this includes: grouping the working data uploaded by multiple preset multi-data fusion sensors based on the chronological order of data acquisition, comparing multiple working data in each group to determine the time points where the working data is inconsistent and need to be corrected; grouping and statistically analyzing the multiple inconsistent working data corresponding to the time points to be corrected; determining the group with the most working data, and using the working data in the group with the most working data as the working data corresponding to the time points to be corrected.

[0013] In one implementation of this application, the corrected working data is bound to equipment information, specifically including: dividing the corrected working data into multiple data segments based on a preset data type, and naming the multiple data segments according to a preset naming rule; wherein the preset naming rule includes one or more of the following: the industrial equipment number corresponding to the data segment, the data segment number, and the occurrence time of the data segment; determining a target type set in the set of working data types corresponding to the equipment information; wherein multiple data types in the target type set are the same as the data types of the multiple data segments; storing the multiple data segments into the storage blocks corresponding to the target type set, and establishing an association relationship between the multiple data segments and the equipment information, so as to bind the multiple data segments to the equipment information.

[0014] In one implementation of this application, before analyzing the bound work data based on historical work data and a pre-set model training library, and outputting the operating information of industrial equipment based on the analysis results, the method further includes: processing the acquired historical work data to generate standardized data; processing the standardized data to generate an industrial equipment operating status database; continuously training the data in the industrial equipment operating status database using the long short-term memory of a recurrent neural network to associate the standardized data stored in the industrial equipment operating status database with the operating status of the industrial equipment, forming an industrial equipment operating status prediction model; analyzing the bound work data based on historical work data and a pre-set model training library, and outputting the operating information of the industrial equipment based on the analysis results, specifically including: converting the received work data into standardized data, and inputting the converted standardized data into the industrial equipment operating status prediction model to output the corresponding work status of the industrial equipment; determining multiple historical work states corresponding to the industrial equipment; inputting the work state and historical work states into a pre-set industrial equipment operating trend prediction model to obtain the corresponding operating trend prediction data of the industrial equipment; and obtaining the corresponding operating information of the industrial equipment based on the corresponding work state and the operating trend prediction data.

[0015] This application provides an industrial equipment status monitoring device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: collect working data of the industrial equipment through multiple preset multi-data fusion sensors, and encrypt and store the collected working data; receive data information uploaded by multiple preset multi-data fusion sensors in real time; wherein the data information includes at least encrypted working data and a device identification code corresponding to the industrial equipment; upload the received device identification code to an identification resolution node for parsing to obtain the device information corresponding to the device identification code; group and compare the working data uploaded by multiple preset multi-data fusion sensors according to the time sequence of the collected working data, correct the working data in each group based on the comparison results, and bind the corrected working data with the device information respectively; analyze the bound working data based on historical working data and a preset model training library, and output the operating information of the industrial equipment based on the analysis results, so as to monitor the status of the industrial equipment through the operating information.

[0016] This application provides a non-volatile computer storage medium storing computer-executable instructions. These instructions are configured to: collect operational data from industrial equipment using multiple pre-set multi-data fusion sensors and encrypt and store the collected data; receive data information uploaded by the multiple pre-set multi-data fusion sensors in real time; wherein the data information includes at least the encrypted operational data and the equipment identification code corresponding to the industrial equipment; upload the received equipment identification code to an identification resolution node for parsing to obtain the equipment information corresponding to the equipment identification code; group and compare the operational data uploaded by the multiple pre-set multi-data fusion sensors based on the chronological order of the collected operational data, correct the operational data in each group based on the comparison results, and bind the corrected operational data to the equipment information; analyze the bound operational data based on historical operational data and a pre-set model training library, and output the operational information of the industrial equipment based on the analysis results, thereby monitoring the status of the industrial equipment through the operational information.

[0017] The at least one technical solution adopted in this application embodiment can achieve the following beneficial effects: By receiving data information uploaded by multiple pre-set multi-data fusion sensors in real time, this application embodiment can determine the working data corresponding to each device based on the device information in the data information. This allows for the comparison of multiple working data corresponding to the same device to determine whether the working data corresponding to the same device is consistent, and then correcting any inconsistent working data to ensure the accuracy of the data corresponding to each industrial device. Secondly, based on historical working data and a pre-set model training library, this application embodiment analyzes the bound working data to determine the current operating status of the industrial equipment, thereby enabling real-time monitoring of the industrial equipment and ensuring its stable operation. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] In the picture:

[0020] Figure 1 A flowchart of an industrial equipment condition monitoring method provided in this application embodiment;

[0021] Figure 2 A flowchart illustrating a working data encryption process is provided in this application embodiment;

[0022] Figure 3 This is a schematic diagram of the structure of an industrial equipment condition monitoring device provided in an embodiment of this application. Detailed Implementation

[0023] This application provides an industrial equipment condition monitoring method, device, and medium.

[0024] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0025] As a core component of industrial development, sensors are crucial for industrial transformation and upgrading, and for improving product quality and reliability. They have wide applications in industrial transformation and upgrading, the Internet of Things (IoT), and artificial intelligence (AI). Achieving industrial interconnection requires building a comprehensive industrial sensor interconnection and collaboration system. This system not only needs to connect machines, equipment, personnel, and materials through a platform, but also needs to aggregate, process, and analyze large amounts of industrial data to provide decision-making support for industrial production, thereby enhancing the intelligence level of manufacturing and industrial enterprises.

[0026] Existing sensors are mainly used in industrial production equipment fault monitoring scenarios, but the types of data collected are limited, the spatial range of a single sensor is limited, and once a sensor fails, the equipment data during the fault period is lost and cannot be recovered, making it difficult to accurately monitor the status of industrial equipment.

[0027] This application embodiment receives data from multiple pre-set multi-data fusion sensors in real time, enabling the determination of operational data for each device based on the device information within the data. This allows for comparison of multiple operational data points corresponding to the same device to determine consistency, correcting any inconsistencies and ensuring the accuracy of data for each industrial device. Furthermore, this application embodiment analyzes the bound operational data based on historical operational data and a pre-set model training library to determine the current operating status of the industrial equipment, enabling real-time monitoring and ensuring stable operation.

[0028] The technical solutions proposed in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0029] Figure 1 This is a flowchart illustrating an industrial equipment condition monitoring method provided in an embodiment of this application. Figure 1 As shown, the industrial equipment condition monitoring method includes the following steps:

[0030] S101. Collects working data of industrial equipment through multiple pre-set multi-data fusion sensors, and encrypts and stores the collected working data.

[0031] In one embodiment of this application, the multi-data fusion sensing device proposed in this embodiment includes a multi-data fusion sensor. The hardware structure of the multi-data fusion sensor includes five core parts: a top cover, a battery, a battery compartment, a circuit board, and a base. The device battery uses a polymer lithium battery, which provides magnetic charging and can be used continuously for one year, ensuring normal device operation. The core circuit sensing part is mainly soldered to the circuit board, including the core board circuit, main power supply circuit, WIFI module circuit, vibration sensor interface circuit, infrared sensor interface circuit, and battery detection circuit. The circuit board is connected internally to the base, and a button device is added externally for easy sensor switching. A hole is drilled to connect the indicator light circuit to display the current status of the device as "charging" or "working". The top cover is made of safe and explosion-proof material, which can isolate the internal and external environments of the device when screwed onto the base, ensuring that the core circuit board is not damaged. The multi-data fusion sensor is installed using an external magnetic mounting method.

[0032] Table 1 is a parameter table of the multi-data fusion sensing device provided in the embodiments of this application.

[0033]

[0034] Table 1

[0035] This application's embodiments endow sensors with interconnectivity and collaborative capabilities, achieving unified standards and interfaces, and providing sensors with unified access capabilities. The multi-data fusion sensor allocates 60 bits of storage space in its hardware memory to store identification resolution codes, thereby achieving the purpose of summarizing sensor-collected data, comprehensively analyzing equipment status, and performing predictive maintenance.

[0036] In one embodiment of this application, multiple preset multi-data fusion sensors are used to collect working data from the same industrial equipment. The working data corresponding to the multiple preset multi-data fusion sensors are divided into a first array and a second array. Based on the first array, the second array, and a preset key, the working data corresponding to the multiple preset multi-data fusion sensors is encrypted, and the encrypted working data is stored in the preset storage space corresponding to each of the multiple preset multi-data fusion sensors.

[0037] Specifically, a first preset subkey and a first array are encrypted to obtain a third array; a second preset subkey and a second array are encrypted to obtain a fourth array. The third and fourth arrays are XORed to obtain a fifth array, which is then shifted; the fifth array is then encrypted with the preset third subkey to obtain a sixth array. The fourth and sixth arrays are XORed to obtain a seventh array, which is then shifted and encrypted with the preset fourth subkey. This process continues until the number of subkeys involved in the encryption process exceeds a preset number of subkeys, thus completing the encryption of the working data.

[0038] Specifically, Figure 2 This is a flowchart illustrating a working data encryption process provided in an embodiment of this application. Figure 2 As shown, in this embodiment, multiple preset multi-data fusion sensors are used to collect working data from the same industrial equipment. The working data corresponding to each preset multi-data fusion sensor, i.e., the original plaintext, is divided into a first array A and a second array B. The first array A is added to a preset first subkey to obtain a third array C. The second array B is added to a second subkey to obtain a fourth array D. Next, the third array C and the fourth array D are XORed to obtain a fifth array E. Based on the size of the fourth array D, the fifth array is shifted left by D bits. The fifth array E is then added to a preset second subkey to obtain a sixth array F. The fourth array D is XORed with the sixth array F to obtain a seventh array G. Based on the size of the sixth array F, the seventh array is shifted left by F bits. Next, the seventh array G is added to a preset third subkey to obtain an eighth array H. Based on the above steps, the obtained arrays are continuously added, XORed, and shifted. The sequence number of the currently encrypted preset subkey is compared with the preset sequence number. If the sequence number of the calculated preset subkey is greater than the preset sequence number, the current encryption process is completed, and the encrypted working data is saved to the corresponding storage location of the preset multi-data fusion sensor.

[0039] This application embodiment employs an encryption algorithm to encrypt memory data. As a block cipher algorithm, this algorithm has a 128-bit key length, is simple and easy to implement in hardware, and its large number of iterations is sufficient to ensure data security. Furthermore, it requires minimal memory during encryption, minimizing consumption of sensor resources while maintaining the security of internal device data. In addition, this application embodiment emphasizes memory protection by fine-grained monitoring of memory read, write, and execution behaviors, real-time detection of abnormal behaviors such as stack code execution and memory data overwriting, and efficient defense against vulnerability attacks using an interception module. Hardware virtualization technology is used to track critical business processes in memory, and through business correlation analysis, it monitors applications for multiple reads, hooking, and tampering with business-related memory, protecting core business data assets from theft. Furthermore, based on CPU instruction set monitoring, it monitors memory code and data status, real-time perception of memory data flow and specific program actions, and defense against known viruses.

[0040] S102. Receive data information uploaded by multiple pre-set multi-data fusion sensors in real time. The data information includes at least encrypted working data and the equipment identification code corresponding to the industrial equipment.

[0041] In one embodiment of this application, an internal code for the industrial equipment is generated based on the production base information and the type of the industrial equipment. The production base information includes at least one of the production city code and the production base serial number. Preset node codes corresponding to the top-level node, second-level node, and enterprise node are obtained to generate an identifier prefix code for the industrial equipment. The internal code and the identifier prefix code are combined in a preset order to obtain a reference equipment identifier code for the industrial equipment. The reference equipment identifier code is uploaded to a parsing second-level node for authentication and registration. Upon receiving authentication approval information from the parsing second-level node, the reference equipment identifier code is used as the equipment identifier code for the industrial equipment.

[0042] Specifically, this application embodiment utilizes identifier resolution technology to develop and build an industrial intelligent collaboration platform. Enterprises fill in key information and authenticate themselves through this platform. Specifically, the internal code of the industrial equipment can be determined based on its production city code and production base serial number. An identifier prefix code corresponding to the industrial equipment is generated based on the preset node codes corresponding to the top-level node, second-level node, and enterprise node. The internal code and the identifier prefix code are then combined, for example, with the identifier prefix code first and the internal code second, to obtain a reference equipment identifier code for the industrial equipment. After successful authentication and registration of this reference equipment identifier code at the identifier resolution second-level node, the identifier resolution node assigns a specific, unique identifier code to the enterprise through the industrial intelligent collaboration platform. This identifier code allows access to the enterprise information stored within the identifier resolution node. After successful enterprise registration, enterprises can register and add internal industrial equipment information through the industrial intelligent collaboration platform, ultimately obtaining the specific equipment identifier code.

[0043] Device identification codes are an important tool for collaboration among multiple data fusion sensors. By storing the device identification code in a specific area of ​​the memory of the multiple data fusion sensor, and setting the sensor to upload the device identification code along with the real-time data of the device when transmitting the device to the industrial intelligent collaboration platform after being connected to the network, the identification and positioning of specific industrial equipment can be realized.

[0044] S103. Upload the received device identification code to the identification resolution node for parsing to obtain the device information corresponding to the device identification code.

[0045] In one embodiment of this application, the received device identification code corresponding to the industrial equipment is uploaded to an identifier resolution node. The identifier resolution node parses the device identification code to obtain the production base serial number and a first hash value corresponding to the device identification code. The production base serial number is used to determine the storage block corresponding to the industrial equipment in the blockchain. Based on the first hash value and the storage block, the industrial equipment information corresponding to the device identification code is retrieved.

[0046] Specifically, after the sensor acquires data, it synchronously transmits the acquired relevant equipment status characteristic data and identification code to the industrial intelligent collaboration platform. The industrial intelligent collaboration platform receives the data from the multi-data fusion sensor, parses and processes it, separates the real-time equipment data and the equipment identification code, and then uploads the equipment identification code to the identification resolution node for parsing and querying to obtain detailed equipment identity information, thus completing the connection and binding between the equipment identification information and the real-time monitoring data of the equipment.

[0047] Furthermore, after parsing the received device identifier code through the identifier resolution node, the device's production base serial number and its corresponding hash value can be obtained. The device's production base serial number allows for quick location of the corresponding storage block in the storage area, and the hash value provides the corresponding industrial equipment information.

[0048] S104. Based on the chronological order of the collected working data, the working data uploaded by multiple preset multi-data fusion sensors are grouped and compared. Based on the comparison results, the working data in each group is corrected, and the corrected working data is bound to the device information respectively.

[0049] In one embodiment of this application, based on the chronological order of data collection, the data uploaded by multiple preset multi-data fusion sensors are grouped, and the data in each group are compared to determine the time points where the data is inconsistent and need to be corrected. The inconsistent data corresponding to the time points to be corrected are then grouped and statistically analyzed. The group with the most data is identified, and the data in this group is used as the data corresponding to the time points to be corrected.

[0050] Specifically, the operating data of each industrial device can be collected separately by multiple data fusion sensors; that is, the operating data collected by multiple data fusion sensors may be the same. Therefore, to ensure the accuracy of the operating data, the data acquired from multiple data fusion sensors are grouped and compared.

[0051] Furthermore, based on the acquisition time of the working data, the data corresponding to multiple data fusion sensors are grouped, that is, data uploaded by different data fusion sensors at the same time point are divided into the same group. Multiple data points within the same group are compared. If the data are all the same, it means that the data received by each data fusion sensor within that time period is correct. If there are differences, it means that the data received by the data fusion sensor contains erroneous data. In this case, the data needs to be corrected so that the correct data can be stored.

[0052] Furthermore, when inconsistencies exist among multiple data points within a group, the data within the same group are divided, with identical data points grouped into one category. The number of data points in each category is determined, i.e., how many data fusion sensors uploaded the data to each category. Based on the statistical results, the category with the largest number of data points is identified, and the data in this category is used as the accurate operating data of the industrial equipment at that specific time point and is saved.

[0053] In one embodiment of this application, based on a preset data type, the modified working data is divided into multiple data segments, and each data segment is named according to a preset naming rule. The preset naming rule includes one or more of the following: the industrial equipment number corresponding to the data segment, the data segment number, and the occurrence time of the data segment. A target type set is determined from the set of working data types corresponding to the equipment information, wherein multiple data types in the target type set are the same as the data types of the multiple data segments. The multiple data segments are stored in the storage blocks corresponding to the target type sets, and an association relationship is established between the multiple data segments and the equipment information to bind the multiple data segments to the equipment information.

[0054] Specifically, since the received work data is extensive, including information such as equipment uptime, completed tasks, and the number of malfunctions, the corrected data can be categorized and stored for rapid subsequent retrieval. That is, based on data type, the received data is categorized into multiple data segments, and each segment is named. Keyword retrieval can be performed on the work data to determine its type, thus dividing it into multiple data segments. In this embodiment, the device information corresponds to a preset set of work data types. This set contains multiple data types. After determining the data type of the corrected data segment, the same type is identified within the work data type set to obtain the target type set corresponding to the corrected work data. The multiple data segments corresponding to this work data are then stored in the corresponding blocks of the target type set, binding the multiple data segments to the device information.

[0055] S105. Based on historical working data and a pre-set model training library, analyze the bound working data, and output the operating information of the industrial equipment based on the analysis results, so as to monitor the status of the industrial equipment through the operating information.

[0056] The acquired historical work data is processed to generate standardized data. This standardized data is then further processed to create an industrial equipment operating status database. The database is continuously trained using the long short-term memory (LSTM) of a recurrent neural network to associate the standardized data with the operating status of the industrial equipment, forming an industrial equipment operating status prediction model. Based on historical work data and a pre-built model training library, the bound work data is analyzed. The analysis results are used to output the operating information of the industrial equipment. Specifically, the received work data is converted into standardized data, and this standardized data is input into the industrial equipment operating status prediction model to output the corresponding working status of the industrial equipment. Multiple historical working states for each industrial equipment are identified. The current working status and historical working states are input into a pre-built industrial equipment operating trend prediction model to obtain the corresponding operating trend prediction data. Based on the current working status and the operating trend prediction data, the operating information of the industrial equipment is obtained.

[0057] Specifically, this application embodiment pre-sets an industrial equipment operating status prediction model. The training process involves processing the received historical data of the industrial equipment to generate standardized data, and then using this standardized data to create an industrial equipment operating status database. Based on the data in this industrial equipment operating status database, a pre-set neural network model is trained to obtain the industrial equipment operating status prediction model. That is, the acquired historical operating data is used as input, and the operating status of the industrial equipment corresponding to the historical operating data is used as output to train the neural network model, thereby obtaining the industrial equipment operating status prediction model.

[0058] Furthermore, the currently corrected and stored data is standardized, and the processed data is input into the industrial equipment operation status prediction model. This model allows the determination of the operating status of the industrial equipment corresponding to the current operating data. Further, the multiple operating statuses corresponding to the industrial equipment are sorted according to time sequence, and these sorted statuses are input into a preset industrial equipment operation trend prediction model to obtain the corresponding operation trend prediction data. This data allows the determination of the equipment's operating information.

[0059] This embodiment of the application, upon receiving data from multiple data fusion sensors, retains and analyzes the data. Based on historical data and records from the platform's built-in model training library, it assesses the current status of the equipment, generates a detailed equipment report, and provides reasonable suggestions for maintenance, thus achieving predictive maintenance. Simultaneously, it presents the equipment names and corresponding data information to staff in a list format. Enterprises can search or view various types of equipment and detailed status information within the enterprise on the industrial intelligent collaborative platform, facilitating the optimization and improvement of the enterprise's equipment management system.

[0060] Figure 3 This is a schematic diagram of the structure of an industrial equipment condition monitoring device provided in an embodiment of this application. Figure 3 As shown, the industrial equipment condition monitoring equipment includes:

[0061] At least one processor; and,

[0062] A memory communicatively connected to the at least one processor; wherein,

[0063] The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to:

[0064] The industrial equipment's operating data is collected by multiple pre-set multi-data fusion sensors, and the collected operating data is encrypted and stored.

[0065] The system receives data information uploaded by the multiple pre-set multi-data fusion sensors in real time; wherein the data information includes at least the encrypted working data and the equipment identification code corresponding to the industrial equipment.

[0066] The received device identification code is uploaded to the identification resolution node for parsing to obtain the device information corresponding to the device identification code;

[0067] Based on the chronological order of the collected working data, the working data uploaded by the multiple preset multi-data fusion sensors are grouped and compared. Based on the comparison results, the working data in each group is corrected, and the corrected working data is bound to the device information.

[0068] Based on historical work data and a pre-built model training library, the bound work data is analyzed, and the operation information of the industrial equipment is output based on the analysis results, so as to monitor the status of the industrial equipment through the operation information.

[0069] This application embodiment also provides a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured as follows:

[0070] The industrial equipment's operating data is collected by multiple pre-set multi-data fusion sensors, and the collected operating data is encrypted and stored.

[0071] The system receives data information uploaded by the multiple pre-set multi-data fusion sensors in real time; wherein the data information includes at least the encrypted working data and the equipment identification code corresponding to the industrial equipment.

[0072] The received device identification code is uploaded to the identification resolution node for parsing to obtain the device information corresponding to the device identification code;

[0073] Based on the chronological order of the collected working data, the working data uploaded by the multiple preset multi-data fusion sensors are grouped and compared. Based on the comparison results, the working data in each group is corrected, and the corrected working data is bound to the device information.

[0074] Based on historical work data and a pre-built model training library, the bound work data is analyzed, and the operation information of the industrial equipment is output based on the analysis results, so as to monitor the status of the industrial equipment through the operation information.

[0075] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0076] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0077] The above description is merely an embodiment of this application and is not intended to limit this application. For those skilled in the art, various modifications and variations can be made to the embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the embodiments of this application should be included within the scope of the claims of this application.

Claims

1. A method for monitoring the condition of industrial equipment, characterized in that, The method includes: The industrial equipment's operating data is collected by multiple pre-set multi-data fusion sensors, and the collected operating data is encrypted and stored. The system receives data information uploaded by the multiple pre-set multi-data fusion sensors in real time; wherein the data information includes at least the encrypted working data and the equipment identification code corresponding to the industrial equipment. The received device identification code is uploaded to the identification resolution node for parsing to obtain the device information corresponding to the device identification code; Based on the chronological order of the collected working data, the working data uploaded by the multiple preset multi-data fusion sensors are grouped and compared. Based on the comparison results, the working data in each group is corrected, and the corrected working data is bound to the device information. Based on historical work data and a pre-built model training library, the bound work data is analyzed, and the operation information of the industrial equipment is output based on the analysis results, so as to monitor the status of the industrial equipment through the operation information; The step involves grouping and comparing the working data uploaded by the multiple preset multi-data fusion sensors based on the chronological order of data collection, and correcting the working data in each group based on the comparison results. Specifically, this includes: Based on the order in which the working data is collected, the working data uploaded by the multiple preset multi-data fusion sensors are grouped, and multiple working data in each group are compared to determine the time points where the working data is inconsistent and needs to be corrected. Group and statistically analyze the multiple inconsistent working data corresponding to the time points to be corrected; Identify the group with the largest number of working data, and use the working data in the group with the largest number of working data as the working data corresponding to the time point to be corrected. The step of binding the corrected working data with the device information specifically includes: Based on a preset data type, the corrected working data is divided into multiple data segments, and the multiple data segments are named according to a preset naming rule; wherein, the preset naming rule includes one or more of the following: the industrial equipment number corresponding to the data segment, the number of the data segment, and the occurrence time of the data segment; From the set of working data types corresponding to the device information, a target type set is determined; wherein, multiple data types in the target type set are the same as the data types of the multiple data segments; The multiple data segments are stored in the storage blocks corresponding to the target type set, and the association between the multiple data segments and the device information is established to bind the multiple data segments to the device information.

2. The method for monitoring the condition of industrial equipment according to claim 1, characterized in that, The industrial equipment's operating data is collected through multiple pre-installed multi-data fusion sensors, and the collected data is encrypted and stored. Specifically, this includes: Multiple pre-installed multi-data fusion sensors are used to collect operating data from the same industrial equipment. The working data corresponding to the multiple preset multi-data fusion sensors are divided into a first array and a second array, respectively; Based on the first array, the second array, and the preset key, the working data corresponding to the plurality of preset multi-data fusion sensors are encrypted, and the encrypted working data is stored in the preset storage space corresponding to the plurality of preset multi-data fusion sensors.

3. The method for monitoring the condition of industrial equipment according to claim 2, characterized in that, The encryption of the working data corresponding to the multiple preset multi-data fusion sensors based on the first array, the second array, and the preset key specifically includes: The first array is encrypted with the first subkey to obtain the third array, and the second array is encrypted with the second subkey to obtain the fourth array. The third array and the fourth array are XORed to obtain the fifth array, and the fifth array is shifted; and the fifth array is encrypted with a preset third subkey to obtain the sixth array; The fourth array and the sixth array are XORed to obtain the seventh array, which is then shifted and encrypted with a preset fourth subkey. The encryption of the working data is completed when the number of subkeys participating in the encryption process exceeds the preset number of subkeys.

4. The industrial equipment condition monitoring method according to claim 1, characterized in that, Before receiving the data information uploaded by the multiple preset multi-data fusion sensors in real time, the method further includes: Based on the production base information corresponding to the industrial equipment and the type of the industrial equipment, an internal code for the industrial equipment is generated; wherein, the production base information includes at least one of the production city code and the production base serial number corresponding to the industrial equipment. Obtain the preset node codes corresponding to the top-level node, second-level node, and enterprise node respectively, and generate the identification prefix code corresponding to the industrial equipment based on the preset node codes; Based on a preset order, the internal code of the device is combined with the identifier prefix code to obtain the reference device identifier code corresponding to the industrial device; The reference device identifier is uploaded to the secondary resolution node so that the reference device identifier can be authenticated and registered through the secondary resolution node. After receiving the authentication pass information sent by the secondary parsing node, the reference device identifier code is used as the device identifier code of the industrial equipment.

5. The method for monitoring the condition of industrial equipment according to claim 1, characterized in that, The step of uploading the received device identifier code to the identifier resolution node for parsing to obtain the device information corresponding to the device identifier code specifically includes: The received equipment identification code corresponding to the industrial equipment is uploaded to the identification resolution node, so that the equipment identification code corresponding to the industrial equipment can be parsed by the identification resolution node to obtain the production base serial number and hash value corresponding to the equipment identification code; The storage block corresponding to the industrial equipment is determined in the blockchain using the production base serial number; Based on the hash value and the storage block, the industrial equipment information corresponding to the device identifier code is found.

6. The method for monitoring the condition of industrial equipment according to claim 1, characterized in that, Before analyzing the bound work data based on historical work data and a pre-built model training library, and outputting the operating information of the industrial equipment based on the analysis results, the method further includes: The acquired historical work data is processed to generate standardized data. The standardized data is processed to generate an industrial equipment operating status database; The data in the industrial equipment operation status database is continuously trained using the long short-term memory of a recurrent neural network to associate the standardized data stored in the database with the industrial equipment operation status, thereby forming an industrial equipment operation status prediction model. Based on historical operational data and a pre-built model training library, the bound operational data is analyzed, and the operational information of the industrial equipment is output based on the analysis results, specifically including: The received working data is converted into standardized data, and the converted standardized data is input into the industrial equipment operating status prediction model, so as to output the corresponding working status of the industrial equipment through the industrial equipment operating status prediction model. Multiple historical operating states corresponding to the industrial equipment were determined; The operating status and the historical operating status are input into a preset industrial equipment operation trend prediction model to obtain the corresponding operation trend prediction data of the industrial equipment. Based on the working status of the industrial equipment and the predicted operating trend data, the operating information of the industrial equipment is obtained.

7. An industrial equipment condition monitoring device, comprising: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform an industrial equipment condition monitoring method as described in any one of claims 1-6.

8. A non-volatile computer storage medium storing computer-executable instructions, which, when executed, enable a processor to perform an industrial equipment condition monitoring method as described in any one of claims 1-6.

Images