Factory equipment rapid positioning system
Through sensor fusion algorithm and artificial intelligence technology, accurate positioning and mobile trend prediction of plant equipment is achieved, solving the problem that traditional systems cannot predict equipment mobile trends and failures, and improving production safety and efficiency.
Patent Information
- Application Number
- CN202411107716.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-13
- Publication Date
- 2024-11-15
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional equipment positioning systems cannot predict equipment movement trends in real time, detect potential faults and promptly warnings, which pose production safety hazards.
Adopt advanced sensor fusion algorithms combined with GPS, Bluetooth, Wi-Fi and inertial navigation technology, combined with artificial intelligence algorithms to achieve accurate positioning of devices, mobile trend prediction and potential fault detection, and monitor the equipment from the working area or security in real time through early warning modules. scope.
It realizes high-precision positioning and movement trend prediction of plant equipment, timely warning of potential failures, reduces the risk of production interruption, and improves production safety and efficiency.
Smart Images

Figure CN118962759A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of plant equipment positioning, and in particular to a plant equipment rapid positioning system. Background Art
[0002] A plant usually refers to the production and operation area of an enterprise or factory, where a large number of production equipment, raw materials, finished products and staff are concentrated. In order to ensure the smooth progress of production and the sustainable development of the enterprise, plant management needs to be efficient, accurate and comprehensive. Plant equipment positioning refers to the real-time and accurate location tracking and management of equipment within the plant through specific technical means. Through real-time positioning of equipment, enterprises can quickly understand the location and status of equipment, so as to arrange production plans and resource scheduling more reasonably, reduce waiting time and idle time, and improve production efficiency. Equipment positioning can help enterprises understand the distribution and utilization of equipment, thereby optimizing resource allocation and avoiding equipment idleness and waste. By adopting advanced positioning technology and information management methods, real-time and accurate positioning and management of plant equipment can be achieved, which can improve production efficiency, optimize resource allocation and ensure production safety.
[0003] With the continuous development of industrial production, the number and types of equipment in the factory are increasing, and the demand for real-time positioning and effective management of equipment is becoming more and more urgent. Traditional equipment positioning systems often rely on a single positioning technology, which can only provide the current location of the equipment, and cannot effectively predict the movement trend of the equipment, and it is difficult to discover potential failure risks in advance, and it is also impossible to detect abnormal behavior of the equipment in real time. When the equipment deviates from the preset working area or the specified safety range, it is impossible to issue a warning in time, resulting in many safety hazards in the production process. Therefore, it is necessary to propose a rapid positioning system for plant equipment to solve the problems in the existing technology. Summary of the invention
[0004] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide a rapid positioning system for factory equipment. It can integrate advanced technologies and algorithms to achieve accurate positioning of factory equipment, movement trend prediction, potential fault warning and abnormal behavior detection, so as to ensure production safety and improve production efficiency.
[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a rapid positioning system for plant equipment, the system comprising:
[0006] The positioning acquisition module uses advanced sensor fusion algorithms and combines GPS, Bluetooth, Wi-Fi and inertial navigation technologies to achieve centimeter-level or even millimeter-level accurate positioning of factory equipment;
[0007] A data transmission module is used to quickly and stably transmit the collected positioning data to the data processing module;
[0008] Data processing module, which uses powerful artificial intelligence algorithms to conduct in-depth analysis of device location data and predict device movement trends and potential failures;
[0009] The early warning module is used to set up the abnormal behavior detection function, and immediately trigger an early warning when the equipment deviates from the preset working area and the specified safety range;
[0010] Storage module, used to store historical positioning data, movement trend data and related information of potential faults of the device;
[0011] The display module is used to display the real-time location, movement trajectory, predicted trend and warning information of the device to the user in an intuitive way.
[0012] Furthermore, the specific execution steps of the positioning acquisition module include:
[0013] First, the GPS sensor obtains the initial location coordinates of the device , and its positioning error is ;
[0014] Bluetooth sensor measures the distance between the device and nearby Bluetooth beacons , calculate the preliminary position by trilateration , the calculation formula of trilateration is: in, is the location coordinates of the Bluetooth beacon;
[0015] The Wi-Fi sensor obtains the strength values of multiple Wi-Fi signals received by the device , using the signal propagation model to calculate the estimated position , the signal propagation model formula is: in, For receiving signal strength indication, is the distance between the device and the Wi-Fi access point, is the path loss exponent, is the reference signal strength at a distance of 1 meter;
[0016] Inertial navigation sensors measure the acceleration of a device and angular velocity , the relative displacement is obtained by integration operation .
[0017] Furthermore, the specific execution steps of the positioning acquisition module also include:
[0018] Use the Kalman filter algorithm to fuse the data obtained by the above sensors to obtain the final high-precision device location , the prediction equation of Kalman filter is: , , the update equation is: , , in, is the predicted state vector, is the forecast error covariance matrix, is the state transfer matrix, is the control input matrix, is the process noise covariance matrix, is the Kalman gain, is the observation matrix, is the observation noise covariance matrix, is the observation vector.
[0019] Furthermore, the specific execution steps of the data transmission module include:
[0020] First, the data collection module encapsulates the collected device positioning data and adds the device identification , Collection time Information, forming a data packet ;
[0021] A priority-based queuing algorithm is used to sort data packets. The priority calculation formula is: in, and is the weight coefficient, Indicates the device type;
[0022] Select an appropriate transmission protocol based on the network status and the congestion level of the transmission path. The formula for determining the congestion level is: in, and is the adjustment factor;
[0023] For the selected transport protocol, use the corresponding flow control algorithm.
[0024] Furthermore, the specific execution steps of the data transmission module also include:
[0025] During the transmission process, the data packets are error checked using cyclic redundancy check. The algorithm calculates the generated check code CRC and attaches it to the data packet. The check code calculation formula is: in, is the data packet content, is the predetermined divisor;
[0026] After a packet is successfully transmitted, the receiver sends an acknowledgment.
[0027] Furthermore, the specific execution steps of the data processing module include:
[0028] First, the received device positioning data is cleaned and preprocessed to remove noise and outliers. A mean filter algorithm is used to calculate the average value of each data point. , its filtered value The calculation is as follows: in, is the filter window size;
[0029] Extract key features from the preprocessed data, including the device’s movement speed , acceleration , Dwell time , where the moving speed The calculation formula is: in, and are the device location coordinates at adjacent moments, is the time interval;
[0030] The time series prediction algorithm of the autoregressive integrated moving average model ARIMA is used to model the movement trend of the device. The expression of the ARIMA model is: in, is the backshift operator, and are the autoregressive and moving average operators respectively, is the autoregressive order, is a white noise sequence.
[0031] Furthermore, the specific execution steps of the data processing module also include:
[0032] The machine learning algorithm of the support vector machine is used to classify the operating status data of the equipment and determine whether there is a potential fault. The decision function of the support vector machine is: in, is the Lagrange multiplier, is the sample label, is the kernel function, is the bias term;
[0033] Use historical data to train the above model and adjust the model parameters through cross-validation method;
[0034] The newly received data is input into the trained model, and the movement trend prediction results and potential fault judgments of the equipment are output in real time.
[0035] Furthermore, the specific execution steps of the early warning module include:
[0036] Set the normal working area of the device, with the center coordinates of the device As the reference, set the radius to The spherical working area is expressed as: ;
[0037] Set the safety range of the device, also based on the center coordinates of the device As the basis, set the side length to , , The rectangular safety range of , its equation is expressed as: ;
[0038] Get the current location coordinates of the device in real time ;
[0039] Calculate the distance between the current position of the device and the center of the working area : ;
[0040] Calculate the distance between the device's current location and the center of the safety range exist ,y, Directional Component , , : , , ;
[0041] Determine whether the distance is out of range. , , , , then trigger the warning;
[0042] When an early warning is triggered, corresponding operations are performed according to the preset early warning level and method.
[0043] Furthermore, the specific execution steps of the storage module include:
[0044] Receive device location data, movement trend data and potential fault related information from the data processing module;
[0045] Classify data according to device identification , Timestamp and data types;
[0046] Use hashing algorithm to generate unique index value for each type of data , the hash function is expressed as: in, It is a custom hash function;
[0047] Store the data in the corresponding database table and data structure according to the index value;
[0048] For historical data, archive it according to the preset time period;
[0049] Regularly check storage space usage and storage space utilization rate Exceeding the threshold , then delete some old data according to the importance and access frequency of the data;
[0050] Create data indexes to facilitate quick retrieval and query of data.
[0051] Furthermore, the specific execution steps of the display module include:
[0052] Receive equipment location, movement trajectory, forecast trend and warning information data from the storage module and data processing module;
[0053] The device location coordinates Convert to pixel coordinates on the display screen , the conversion formula is: , in, and are the minimum and maximum coordinates of the device position, respectively. and The width and height of the display screen respectively;
[0054] Draw the real-time location points of the device and use the graphics drawing algorithm to draw smooth points;
[0055] According to the moving trajectory data of the device, the linear interpolation algorithm is used to calculate the coordinates of the middle points on the trajectory to draw a continuous trajectory line. The linear interpolation formula is: , in, and are two adjacent known points on the trajectory, is the interpolation ratio ;
[0056] For the predicted trend of the equipment, a curve fitting algorithm is used to draw the predicted curve. The predicted trend function is: , the coefficients are solved by the least square method to minimize the sum of square errors between the actual data points and the fitting curve. The error calculation formula is: ;
[0057] Display warning information with different colors, icons and flashing effects;
[0058] According to the user's operation, the display content is updated in real time, and the display position and size of the image are adjusted using the matrix transformation algorithm.
[0059] Compared with the existing technology, the plant equipment rapid positioning system has the following beneficial effects:
[0060] The present invention uses advanced sensor fusion algorithms through the positioning and acquisition module to achieve high-precision positioning of factory equipment, which helps to accurately grasp the location of equipment. The data processing module uses artificial intelligence algorithms to conduct in-depth analysis of positioning data, which can predict the movement trend of equipment. The data processing module is used to detect potential faults, warn of potential faults in advance, and reduce the risk of production interruption caused by sudden equipment failures. The abnormal behavior detection function of the early warning module can monitor the location and behavior of the equipment in real time. When the equipment deviates from the preset working area or the specified safety range, it can issue an early warning in time, which can reduce many safety hazards in the production process.
[0061] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0062] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0063] Figure 1 The figure is a structural diagram of a rapid positioning system for factory equipment. DETAILED DESCRIPTION
[0064] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0065] Embodiment 1
[0066] A rapid positioning system for plant equipment, the system comprising:
[0067] The positioning acquisition module adopts advanced sensor fusion algorithms and combines multiple technologies such as GPS, Bluetooth, Wi-Fi and inertial navigation to achieve centimeter-level or even millimeter-level precise positioning of factory equipment. The positioning acquisition module is the foundation of the entire system and is responsible for obtaining the initial location information of the equipment. It adopts advanced sensor fusion algorithms and organically combines multiple positioning technologies to achieve high-precision positioning effects.
[0068] GPS sensors provide the approximate location of equipment around the world, but the signal may be unstable due to obstruction by buildings within the factory. For example, in a large workshop, the GPS signal may be weakened or lost in some areas. Bluetooth sensors communicate with fixed Bluetooth beacons in the surrounding area to measure the distance between the equipment and the beacon, thereby assisting in determining the location of the equipment. For example, in a multi-story factory building, Bluetooth beacons can be installed at stairwells and key passages to provide supplementary information for equipment positioning.
[0069] Wi-Fi sensors use the widely distributed Wi-Fi network in the factory to estimate the location of the device by measuring the strength of the received signal. Assuming that in a warehouse with multiple Wi-Fi access points, the device can determine its own position more accurately based on the signal strength of different access points. The inertial navigation sensor can sense the movement state of the device, including acceleration and angular velocity. Even if other positioning signals are briefly interrupted, the relative displacement of the device can be calculated through integral operations. For example, when the device enters an area with strong electromagnetic interference and other positioning methods are affected, the inertial navigation sensor can still continue to provide certain location information.
[0070] The data transmission module is used to quickly and stably transmit the collected positioning data to the data processing module. The data transmission module is a bridge connecting the positioning acquisition module and the subsequent processing module, ensuring that the positioning data can be quickly, accurately and completely transmitted to the data processing center.
[0071] The module uses efficient communication protocols, such as the MQTT protocol, which is lightweight, has low bandwidth occupancy and reliable transmission. At the same time, 5G networks or industrial-grade Wi-Fi networks are used as transmission media to meet the needs of high-speed transmission of large amounts of data. In order to ensure the timeliness of data, a real-time transmission mechanism is adopted. For example, for some key equipment, the data transmission interval can be set to once per second to ensure that its location and status can be monitored in real time. During the data transmission process, data compression technology is also used to reduce the amount of data and improve transmission efficiency. At the same time, the data is encrypted by an encryption algorithm to ensure the security and privacy of the data. In addition, the data transmission module has a breakpoint resume function. If a network interruption occurs during the transmission process, when the network is restored, the data can continue to be transmitted from the breakpoint to ensure that the data is not lost.
[0072] The data processing module is used to use powerful artificial intelligence algorithms to conduct in-depth analysis of equipment positioning data and predict equipment movement trends and potential failures. The data processing module is the core brain of the system. It uses powerful artificial intelligence algorithms to conduct in-depth analysis and mining of equipment positioning data. By adopting machine learning algorithms, it classifies and evaluates the operating status of the equipment. For example, based on the equipment's movement speed, acceleration, dwell time and other characteristics, it determines whether the equipment is in normal working condition or has an abnormality. At the same time, the anomaly detection algorithm is used to promptly detect abnormal points and abnormal patterns in the equipment positioning data. If the equipment suddenly deviates significantly from the normal trajectory, it can quickly judge and issue an alarm.
[0073] The early warning module is used to set the abnormal behavior detection function. When the equipment deviates from the preset working area and the specified safety range, the early warning is immediately triggered. The early warning module is an important line of defense to ensure production safety and prevent abnormal situations.
[0074] The early warning module sets up a variety of abnormal behavior detection rules, including not only the equipment deviating from the preset working area or the designated safety range, but also the abnormal movement speed of the equipment, the long stay time, etc. For example, if a crane does not move to the designated working position within the specified time, or the movement speed exceeds the safety limit, the system will immediately trigger an early warning.
[0075] There are various warning methods, including sound alarms, flashing lights, SMS notifications, application push, etc. In a noisy production environment, the sound alarm can use a high-decibel sirens; at night or in dimly lit areas, flashing lights can be more eye-catching.
[0076] The storage module is used to store the device's historical positioning data, movement trend data, and related information on potential faults. It uses a combination of relational databases (such as MySQL) and non-relational databases (such as MongoDB). The relational database is used to store structured data, such as basic information about the device, warning records, etc., while the non-relational database is used to store a large amount of unstructured data, such as the device's movement trajectory data.
[0077] In order to improve the efficiency of data query and retrieval, a suitable index structure is established. For example, indexes are created for commonly used query fields such as device identification and timestamp to speed up data access. At the same time, the storage module also has data cleaning and archiving functions. For data that exceeds a certain retention period, it will be archived to save storage space. However, before archiving, the integrity and recoverability of the data will be ensured.
[0078] The display module is used to display the real-time location, movement trajectory, predicted trend and warning information of the device to the user in an intuitive manner. The display module presents relevant information of the device to the user in an intuitive, clear and easy-to-understand manner.
[0079] It adopts a display method that combines electronic maps and charts. The real-time location and movement trajectory of the equipment are accurately marked on the electronic map. Users can view the distribution of equipment in different areas by zooming and panning the map. For example, on a map of a large industrial park, the location and movement trajectory of the equipment in each workshop can be clearly seen.
[0080] It provides multi-dimensional filtering and sorting functions. Users can filter and sort the displayed data according to conditions such as equipment type, work area, warning level, etc. For example, users can only view the equipment information at a high warning level, or only focus on the equipment in a specific work area.
[0081] At the same time, the display module supports real-time data updates to ensure that the information users obtain is always the latest, and has interactive functions. Users can obtain detailed information and related operation options of the device by clicking, dragging, and other operations.
[0082] Embodiment 2
[0083] Based on the first embodiment, this embodiment describes in detail the overall workflow of a system for rapid positioning of plant equipment.
[0084] First, various sensors in the positioning acquisition module obtain the device's location information in real time. The GPS sensor sends the device's latitude, longitude and altitude coordinate information at a certain frequency; the Bluetooth sensor continuously measures the distance between the device and the surrounding Bluetooth beacons, and transmits this distance data to the positioning acquisition module; the Wi-Fi sensor continuously scans the surrounding Wi-Fi signals to obtain signal strength values; the inertial navigation sensor collects the device's acceleration and angular velocity data in real time. The data obtained by these sensors will be preliminarily fused in the positioning acquisition module, and the accuracy of positioning will be preliminarily improved through algorithms such as weighted averaging.
[0085] Then, the data after preliminary fusion processing is received by the data transmission module. The data transmission module first compresses and encodes the data to reduce the amount of data and improve transmission efficiency. The compression coding algorithm used calculates the frequency of occurrence of characters in the data, assigns shorter codes to frequently appearing characters, and assigns longer codes to less frequently appearing characters. The encoded data is divided into fixed-size data packets, and a serial number and check code are added to each data packet to ensure the integrity and accuracy of the data.
[0086] Next, the data transmission module selects the optimal transmission path and protocol based on the current network conditions. If the network bandwidth is sufficient and the latency is low, the TCP protocol is selected for transmission to ensure reliable data arrival. If the network conditions are poor, the UDP protocol is selected for transmission, sacrificing a certain degree of reliability in exchange for transmission speed. During the transmission process, the data transmission module will also monitor the network congestion in real time and use congestion control algorithms, such as slow start and congestion avoidance algorithms, to adjust the data sending rate.
[0087] Then, after receiving the transmitted data, the data processing module first performs decompression and decoding operations to restore the original data, and then cleans and preprocesses the data to remove outliers and noise. The cleaning algorithm used is, for example, a statistical outlier detection algorithm, which calculates the mean and standard deviation of the data, and regards data that deviates from the mean by more than a certain standard deviation as outliers and processes them.
[0088] The preprocessed data is input into the deep analysis model. For the prediction of equipment movement trend, a time series prediction model based on neural network is used to model the movement trend of the equipment to predict the future location change trend. For the detection of potential faults, a classification model based on machine learning is used, such as support vector machine (SVM). These models analyze the operating status data of the equipment, such as vibration, temperature, etc., to determine whether there is a potential fault.
[0089] The early warning module continuously receives the equipment location, movement trend and potential fault information output by the data processing module. The early warning module compares the real-time equipment location with the preset working area and safety range. If the equipment location exceeds the preset range, an early warning is triggered immediately. For the early warning of equipment movement trend, when the predicted movement trend indicates that the equipment may enter a dangerous area or move abnormally, an early warning will also be triggered. The early warning of potential faults is based on the output results of the fault detection model. When it is detected that the equipment has a high risk of failure, a corresponding early warning signal is issued.
[0090] The storage module classifies and stores all relevant data, including the original positioning data of the equipment, the processed location and movement trend data, the detection results of potential faults, and early warning information. The storage module uses a database management system, such as MySQL or MongoDB, to organize and store data according to time series and device identification for subsequent query and analysis.
[0091] Finally, the display module obtains real-time data and historical data from the storage module or the data processing module, and displays them to the user in an intuitive manner. On the display interface, the real-time location of the device is presented in the form of a map, the movement trajectory is drawn in the form of a line, the predicted trend is presented in the form of a curve, and the early warning information is displayed in prominent colors and icons. Users can view data from different time periods and obtain detailed information about the device through interactive operations such as zooming and panning the map.
[0092] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the same elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.
Claims
1. A rapid positioning system for factory equipment, characterized in that: The system includes: Positioning acquisition module, which uses advanced sensor fusion algorithms and combines GPS, Bluetooth, Wi-Fi, and inertial navigation technologies to achieve precise positioning of factory equipment; The data transmission module is used to quickly and stably transmit the collected positioning data to the data processing module; A data processing module, which uses powerful artificial intelligence algorithms to conduct in-depth analysis of device location data and predict device movement trends and potential failures; The early warning module is used to set up abnormal behavior detection functions, and immediately trigger an early warning when the equipment deviates from the preset working area and the specified safety range; Storage module, used to store historical positioning data, movement trend data and information related to potential faults of the device; The display module is used to display the real-time location, movement trajectory, predicted trends and warning information of the device to the user in an intuitive manner.
2. A factory equipment rapid positioning system according to claim 1, characterized in that: The specific execution steps of the positioning acquisition module include: First, the GPS sensor obtains the initial location coordinates of the device , and its positioning error is ; Bluetooth sensors measure the distance between a device and nearby Bluetooth beacons , calculate the preliminary position by trilateration , the calculation formula of trilateration is: in, is the location coordinates of the Bluetooth beacon; The Wi-Fi sensor obtains the strength values of multiple Wi-Fi signals received by the device , using the signal propagation model to calculate the estimated position , the signal propagation model formula is: in, For receiving signal strength indication, is the distance between the device and the Wi-Fi access point, is the path loss exponent, is the reference signal strength at a distance of 1 meter; Inertial navigation sensors measure the acceleration of a device and angular velocity , the relative displacement is obtained by integration operation .
3. A factory equipment rapid positioning system according to claim 2, characterized in that: The specific execution steps of the positioning acquisition module also include: Use the Kalman filter algorithm to fuse the data obtained by the above sensors to obtain the final high-precision device location , the prediction equation of Kalman filter is: , , the update equation is: , , in, is the predicted state vector, is the forecast error covariance matrix, is the state transition matrix, is the control input matrix, is the process noise covariance matrix, is the Kalman gain, is the observation matrix, is the observation noise covariance matrix, is the observation vector.
4. A factory equipment rapid positioning system according to claim 1, characterized in that: The specific execution steps of the data transmission module include: First, the data acquisition module encapsulates the collected device positioning data and adds the device identification , collection time Information, forming data packets ; A priority-based queuing algorithm is used to sort data packets. The priority calculation formula is: in, and is the weight coefficient, Indicates the device type; Select an appropriate transmission protocol based on the network conditions and the degree of congestion in the transmission path. The formula for determining the degree of congestion is: in, and is the adjustment factor; For the selected transport protocol, use the corresponding flow control algorithm.
5. A factory equipment rapid positioning system according to claim 4, characterized in that: The specific execution steps of the data transmission module also include: During the transmission process, the data packets are error checked using cyclic redundancy check. The algorithm calculates the generated check code CRC and appends it to the data packet. The check code calculation formula is: in, is the data packet content, is the predetermined divisor; After the data packet is successfully transmitted, the receiver sends an acknowledgment.
6. A factory equipment rapid positioning system according to claim 1, characterized in that: The specific execution steps of the data processing module include: First, the received device positioning data is cleaned and preprocessed to remove noise and outliers. A mean filter algorithm is used to calculate the average value of each data point. , its filtered value The calculation is as follows: in, is the filter window size; Extract key features from the preprocessed data, including the device's movement speed , acceleration , residence time , where the moving speed The calculation formula is: in, and is the device position coordinate at adjacent moments, is the time interval; The time series prediction algorithm of the autoregressive integrated moving average model ARIMA is used to model the movement trend of the device. The expression of the ARIMA model is: in, is the backshift operator, and are the autoregressive and sliding average operators respectively, is the autoregressive order, is a white noise sequence.
7. A factory equipment rapid positioning system according to claim 6, characterized in that: The specific execution steps of the data processing module also include: The machine learning algorithm of the support vector machine is used to classify the operating status data of the equipment and determine whether there is a potential fault. The decision function of the support vector machine is: in, is the Lagrange multiplier, is the sample label, is the kernel function, is the bias term; Use historical data to train the above model and adjust the model parameters through cross-validation method; The newly received data is input into the trained model, and the device's movement trend prediction results and potential fault judgments are output in real time.
8. The rapid positioning system for factory equipment according to claim 1, characterized in that: The specific execution steps of the early warning module include: Set the normal working area of the device, with the center coordinates of the device As a reference, set the radius to The spherical working area is expressed as follows: ; Set the safety range of the device, also based on the center coordinates of the device As a reference, set the side length to 、 、 The rectangular safety range of , its equation is expressed as: ; Get the current location coordinates of the device in real time ; Calculate the distance between the device's current position and the center of the working area : ; Calculate the distance between the device's current location and the center of the safety range exist 、y、 Directional component 、 、 : , , ; Determine whether the distance is out of range. 、 、 、 , then trigger the warning; When the warning is triggered, corresponding operations are performed according to the preset warning level and method.
9. The rapid positioning system for factory equipment according to claim 1, characterized in that: The specific execution steps of the storage module include: Receive device location data, movement trend data, and potential fault information from the data processing module; Classify data according to device identification , timestamp and data types; Use hashing algorithm to generate unique index value for each type of data , the hash function is expressed as: in, It is a custom hash function; Store data in corresponding database tables and data structures according to index values; For historical data, archive it according to the preset time period; Regularly check storage space usage and storage space utilization rate Exceeding the threshold , then delete some old data according to the importance and access frequency of the data; Create data indexes for quick data retrieval and query.
10. The rapid positioning system for factory equipment according to claim 1, characterized in that: The specific execution steps of the display module include: Receive device location, movement trajectory, forecast trend and warning information data from the storage module and data processing module; The device location coordinates Convert to pixel coordinates on the display screen , the conversion formula is: , in, and are the minimum and maximum coordinates of the device position, respectively. and The width and height of the display screen respectively; Draw the real-time location points of the device and use the graphics drawing algorithm to draw smooth points; According to the device's movement trajectory data, a linear interpolation algorithm is used to calculate the coordinates of the intermediate points on the trajectory to draw a continuous trajectory line. The linear interpolation formula is: , in, and are two adjacent known points on the trajectory, is the interpolation ratio ; For the predicted trend of the equipment, a curve fitting algorithm is used to draw the predicted curve. The predicted trend function is: , solve the coefficients by the least square method to minimize the sum of square errors between the actual data points and the fitted curve. The error calculation formula is: ; Display warning information with different colors, icons and flashing effects; According to the user's operation, the display content is updated in real time, and the display position and size of the image are adjusted using the matrix transformation algorithm.
Citation Information
Patent Citations
Packet loss recovery method and device for data transmission network and computer equipment
CN110391879A
Industrial internet business management system
CN112988865A
Outdoor operation safety monitoring method based on indoor and outdoor positioning system
CN117496431A
Intelligent industrial Internet of Things terminal detection system
CN118228122A
Positioning management method and related equipment
CN118446660A
Cited By
Multi-data fusion method and system based on edge calculation
CN119598404A
A multi-data fusion method and system based on edge computing
CN119598404B
Control method and system for intelligent anti-lost equipment
CN120544352A
A control method and system for intelligent anti-lost device
CN120544352B
