Measure normal and abnormal waveforms

The bolt-type piezoelectric load sensor PiezoBolt detects minute differences in force and vibration that could not be measured before.

Realization of edge computing environment

Easily realize IoT without going through servers or internal networks. Simplifies cumbersome data management.

Abnormal signals are transmitted according to the purpose.

Visualization of facility operation status can be achieved by setting different signals for normal, caution, and error status after setting threshold values.

Real-time anomaly detection

The measured data can be monitored in real time to monitor the current state of the equipment and the state of molding.

Big Data Analysis

By analyzing and utilizing data collected in the past, it is possible to analyze in detail phenomena occurring at processing points that were previously invisible.

Machine learning system

By utilizing the accumulated data and allowing the system to learn, more accurate decisions can be made.

Household (electrical) appliance manufacturer

It is used to detect minute abnormalities in parts at mass production sites. Abnormalities in parts were sometimes found during assembly, but now defects can be identified in-process.

Automotive parts manufacturer

By visualizing equipment operating conditions, we detect product and equipment malfunctions.Especially for facilities, the data is used to determine the timing of maintenance from the viewpoint predictive maintenance.

Equipment manufacturer

It is used to determine the timing of parts replacement from the perspective of equipment maintenance. Longer delivery time of parts allows us to order parts at the right time before they break, leading to improved utilization rates.

Rubber Products Manufacturer

It is used to measure the durability and characteristics of products during the IoT study phase and to analyze the factors that contribute to quality variation. We are working to integrate simulation results with sensing results.

Electronic component manufacturer

This is an example of using IoT to standardize defect management, which used to rely on skilled workers. Now anyone can see the signs of abnormalities and their occurrence by looking at the waveforms, making process management easier.

Lubricants Manufacturer

We visualized the occurrence of friction due to changes in lubrication conditions and types, and used this data for the development of new products. We were able to detect minute differences in conditions and determine the optimal conditions.

Automaker

IoT is incorporated into the manufacturing and used to detect abnormalities in equipment malfunctions. The real-time monitoring of equipment conditions and predictive maintenance has made it possible to prevent production stoppages due to sudden equipment breakdowns.

Medical device manufacturer

It is applied to the manufacture of products that require very severe accuracy. In addition to detecting product defects, the system can visualize the relationship between molding conditions and equipment defects, and is also used to determine optimal molding conditions. It is also useful for traceability.

Kitchen equipment manufacturer

Our solution was introduced with the goal of creating a smart factory through IoT at the manufacturing site. It is now possible to check for minute defects in products that are difficult to see with the human eye, preventing defective products from being passed on.

For die breakage detection

Issue:
Standardization of die life management for quantification

Effect:
・Simplified die condition check process
・Dies can be used continuously until the life of the die is determined to be over.
・Die life evaluation based on quantitative criteria is possible

10% increase in production efficiency ⇒ 1.5 million yen/month
Simplified die inspection process ⇒ 100,000 yen/month
50% increase in die life ⇒ 4 million yen/month
Annual Cost Effectiveness　23.2 million yen/year

*Our calculations

In case of product defect detection

Issue:
Detection of product shape defects

Effect:
・Avoid quality problems due to outflow of defective products
・Simplified product inspection methods
・Low investment cost

Zero outflow of defective products ⇒ 500,000 yen/month
Reduction of 1 inspector ⇒ 300,000 yen/month
20% increase in production efficiency ⇒ 2 million yen/month
Annual cost effectiveness　33.6 million yen/year

*Our calculations

For detecting abnormalities in the cutting process

Issue:
Automation and unmanned cutting processes

Effect:
・Real-time monitoring during cutting process
・Can be realized at a low cost
・Break away from relying on people's intuition

Increased productivity through unmanned operations ⇒ 300,000 yen/month
Prevention of secondary disasters due to tool breakage ⇒ 60,000 yen/month
Annual cost effect 　2.88 million yen/year

*Our calculations